© 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. 12311
    Prev
    Next
    INDEX
    Explanations

    forwards

    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
    venting
    -0.07
    描绘
    -0.07
    toy
    -0.06
    catalog
    -0.06
    |.
    -0.06
     Developing
    -0.06
    ᠦ
    -0.06
     อ
    -0.06
     nº
    -0.06
    一批
    -0.06
    POSITIVE LOGITS
    ız
    0.08
     Composite
    0.07
     LES
    0.07
    EndDate
    0.07
    ır
    0.07
     DIV
    0.07
     IMPLIED
    0.07
    +-+-+-+-
    0.07
     unbiased
    0.07
     Neighbor
    0.07
    Activations Density 0.011%

    No Known Activations