© 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. 19-RESID-POST-AA
    11. 7585
    Prev
    Next
    INDEX
    Explanations

    code benchmark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    划分
    -0.08
    apan
    -0.08
     ана
    -0.08
     учет
    -0.07
     אותם
    -0.07
     naam
    -0.07
    chw
    -0.07
    _snap
    -0.07
     Kai
    -0.07
     opcion
    -0.07
    POSITIVE LOGITS
    give
    0.08
    敌
    0.08
    strument
    0.08
     around
    0.08
     Stones
    0.07
     Near
    0.07
    틍
    0.07
    为代表
    0.07
     pedestrian
    0.07
     restricting
    0.07
    Activations Density 0.002%

    No Known Activations