© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42480
    Prev
    Next
    INDEX
    Explanations

    Bryn Mawr

    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
    Negative Logits
    怎么做
    -0.08
    ESSAGE
    -0.07
    답
    -0.07
    웁
    -0.07
     pessoa
    -0.07
    ='-
    -0.07
    עס
    -0.07
    URE
    -0.07
     ככה
    -0.07
    ER
    -0.06
    POSITIVE LOGITS
     committing
    0.07
    THOOK
    0.07
    _checker
    0.07
     profoundly
    0.07
     Cath
    0.07
    Mozilla
    0.06
    batis
    0.06
     (...)
    0.06
     shear
    0.06
    истем
    0.06
    Activations Density 0.002%

    No Known Activations