© 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. 11-RESID-POST-AA
    11. 56988
    Prev
    Next
    INDEX
    Explanations

    of

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     puppies
    -0.08
    (mesh
    -0.07
    郗
    -0.07
    瞻
    -0.07
     dele
    -0.06
     PureComponent
    -0.06
     التاريخ
    -0.06
    غض
    -0.06
    \HttpFoundation
    -0.06
     RANDOM
    -0.06
    POSITIVE LOGITS
    报道称
    0.07
    _Dis
    0.07
     area
    0.07
    Qualified
    0.06
    ള
    0.06
    ill
    0.06
    运行
    0.06
    /hr
    0.06
    -Line
    0.06
     apt
    0.06
    Activations Density 0.010%

    No Known Activations