© 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. 49899
    Prev
    Next
    INDEX
    Explanations

    provide

    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
     Facing
    -0.08
     ن
    -0.08
     الن
    -0.07
     الشخصية
    -0.07
     tránh
    -0.07
    -overlay
    -0.07
    .instance
    -0.07
    فة
    -0.07
     الصحيح
    -0.06
    န
    -0.06
    POSITIVE LOGITS
    욤
    0.07
    vod
    0.07
    新品
    0.07
    _clear
    0.07
    sembl
    0.06
    sembled
    0.06
    coded
    0.06
    _definitions
    0.06
    metal
    0.06
     magistrate
    0.06
    Activations Density 0.020%

    No Known Activations