© 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. 40254
    Prev
    Next
    INDEX
    Explanations

    cheese/bacteri

    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
    -makers
    -0.09
    éģĩ
    -0.08
    åIJĮ缣
    -0.08
    luent
    -0.08
    cling
    -0.08
    oren
    -0.08
     воÑģ
    -0.07
     план
    -0.07
    structor
    -0.07
    ãģ©
    -0.07
    POSITIVE LOGITS
    åħ±åĴĮåĽ½
    0.10
    ness
    0.10
    iez
    0.10
    éŃij
    0.09
    orro
    0.09
    NESS
    0.09
    è¤
    0.09
    ewe
    0.09
    å¸®ä½ł
    0.09
    æ§Ľ
    0.09
    Activations Density 0.002%

    No Known Activations