© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55941
    Prev
    Next
    INDEX
    Explanations

    if clauses

    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
    Not in Any Lists

    No Comments

    Negative Logits
    agi
    -0.11
    amon
    -0.09
    åĩł
    -0.09
    çĽĬ
    -0.08
     singleton
    -0.08
    евиÑĩ
    -0.08
    å°±æĺ¯åľ¨
    -0.08
    ä¸į论
    -0.08
    ами
    -0.08
    ç»Ń
    -0.08
    POSITIVE LOGITS
    ToEnd
    0.09
    åį«æĺŁ
    0.09
    isz
    0.09
    ãĥĽãĥ¼ãĥł
    0.08
     fos
    0.08
     jaws
    0.08
    羣æŃ£åģļåĪ°
    0.08
    åĽŀäºĭ
    0.08
    éĻIJéĩı
    0.08
    å¾ĹåĪ°æľīæķĪ
    0.08
    Activations Density 0.021%

    No Known Activations