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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 85321
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash

    Promotional/product copy about saving time (often in the phrase "save you time and money") or similar marketing phrases.

    oai_token-act-pair · gpt-5-miniTriggered 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
     corrected
    -0.07
    _Mode
    -0.07
    -save
    -0.07
     Choice
    -0.07
     Мари
    -0.07
    嗓
    -0.07
    move
    -0.07
     economy
    -0.07
     congregation
    -0.07
    (optimizer
    -0.07
    POSITIVE LOGITS
    /videos
    0.08
    渔业
    0.07
    送去
    0.07
    标签
    0.07
    imagenes
    0.07
    ERSHEY
    0.07
    וצאות
    0.07
    favicon
    0.07
    iggins
    0.07
    做大
    0.07
    Activations Density 0.474%

    No Known Activations