© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 28600
    Prev
    Next
    INDEX
    Explanations

    Non-english language

    np_max-act · gemini-2.0-flash

    non-English (especially Romance and Slavic) content words in user prompts, with a strong bias toward formal nouns and request/description phrasing.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     скоро
    -0.07
    ledged
    -0.07
     atheist
    -0.07
     לאחרונה
    -0.07
    locker
    -0.07
    Davis
    -0.07
    /Main
    -0.07
    突如其来
    -0.07
    狷
    -0.06
    በ
    -0.06
    POSITIVE LOGITS
    貼
    0.08
    tex
    0.07
     """
    ↵
    ↵
    0.06
     MET
    0.06
     Outputs
    0.06
    病理
    0.06
     seating
    0.06
    肖
    0.06
    Old
    0.06
    pq
    0.06
    Activations Density 0.411%

    No Known Activations