Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 20402
    Prev
    Next
    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    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
    Ѷ
    -0.07
     Manual
    -0.06
    入
    -0.06
    otta
    -0.06
    Ӏ
    -0.06
    acro
    -0.06
     f
    -0.06
     cares
    -0.06
    azu
    -0.06
    cobra
    -0.06
    POSITIVE LOGITS
    /ros
    0.08
    ではなく
    0.08
     Rivera
    0.08
    温度
    0.07
    货物
    0.07
     прожива
    0.07
     humidity
    0.07
    躺
    0.07
    首饰
    0.07
    _address
    0.07
    Activations Density 0.007%

    No Known Activations