© 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. 40240
    Prev
    Next
    INDEX
    Explanations

    walking

    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
    çĽ¾
    -0.11
    é©°
    -0.10
    èĥĨ
    -0.10
    çĮľæĥ³
    -0.09
    çħŀ
    -0.09
    éĺĻ
    -0.09
    ç³Ł
    -0.09
    åŤ
    -0.09
    aira
    -0.09
    躺
    -0.09
    POSITIVE LOGITS
    .walk
    0.17
    æŃ¥è¡Į
    0.15
     walking
    0.15
     Walking
    0.14
     walks
    0.14
     walk
    0.14
     Walk
    0.14
     walked
    0.14
    Walking
    0.14
    walking
    0.13
    Activations Density 0.062%

    No Known Activations