© 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. 52464
    Prev
    Next
    INDEX
    Explanations

    online forum posts

    np_max-act · gemini-2.0-flash

    first-person, forum-style narratives where someone describes their own situation or problem, often with temporal details and ongoing actions.

    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
    #[
    -0.07
    [MAXN
    -0.06
    -modal
    -0.06
    administr
    -0.06
    Nos
    -0.06
     Jiang
    -0.06
    position
    -0.06
    cation
    -0.06
     ],
    -0.06
     SKF
    -0.06
    POSITIVE LOGITS
    _DELAY
    0.07
    volatile
    0.07
    阁
    0.06
     sağlık
    0.06
    記事
    0.06
     바랍니다
    0.06
    サラ
    0.06
    Delayed
    0.06
    注明出处
    0.06
    trap
    0.06
    Activations Density 0.138%

    No Known Activations