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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 82868
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    浅
    -0.07
    dos
    -0.07
    쩐
    -0.07
     applaud
    -0.07
    <|im_start|>
    -0.07
    ڠ
    -0.06
    コン
    -0.06
     think
    -0.06
    ��
    -0.06
     Loy
    -0.06
    POSITIVE LOGITS
    إقامة
    0.08
    xEB
    0.07
     DatePicker
    0.07
    _cats
    0.07
     CGRect
    0.07
    做工
    0.07
     lifes
    0.07
    穿戴
    0.07
     UART
    0.07
    צב
    0.07
    Activations Density 0.082%

    No Known Activations