© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12427
    Prev
    Next
    INDEX
    Explanations

    proper nouns and descriptive nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ترÙĥ
    -0.07
     Dank
    -0.07
    CAA
    -0.07
    apg
    -0.07
    fk
    -0.06
    éĢıè¿ĩ
    -0.06
     Clemson
    -0.06
    äºĮèĢħ
    -0.06
     muj
    -0.06
     Incorporated
    -0.06
    POSITIVE LOGITS
    _EDEFAULT
    0.11
     Geile
    0.10
    iếc
    0.09
     سبØŃ
    0.09
    èĮĨ
    0.09
    .IsNullOr
    0.09
    há»ķ
    0.09
     Câm
    0.09
    .updateDynamic
    0.09
    onga
    0.09
    Activations Density 0.387%

    No Known Activations