© 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. 7-RESID-POST-AA
    11. 82502
    Prev
    Next
    INDEX
    Explanations

    in

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vib
    -0.07
     Collector
    -0.07
    _YUV
    -0.07
    Prediction
    -0.07
     accordion
    -0.07
    ibur
    -0.07
    导向
    -0.07
     Detector
    -0.07
    那只
    -0.07
    -how
    -0.06
    POSITIVE LOGITS
    igh
    0.08
     MEDIATEK
    0.07
    Tele
    0.07
    (origin
    0.07
     compañero
    0.07
     najbliższ
    0.06
    строен
    0.06
    كم
    0.06
     chaired
    0.06
    okableCall
    0.06
    Activations Density 0.058%

    No Known Activations