© 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. 37634
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Explos
    -0.07
    vous
    -0.07
     מאז
    -0.07
    孖
    -0.07
    沧桑
    -0.07
     Bud
    -0.07
     Levels
    -0.07
     srand
    -0.06
     sie
    -0.06
     בהם
    -0.06
    POSITIVE LOGITS
    (parsed
    0.07
    ikel
    0.07
    ollection
    0.07
    refix
    0.07
    enses
    0.07
    ieri
    0.07
    ROME
    0.07
    我国
    0.07
    ioni
    0.07
    Isn
    0.07
    Activations Density 0.080%

    No Known Activations