© 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. 30251
    Prev
    Next
    INDEX
    Explanations

    version numbers with file extensions

    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
    íħį
    -0.09
    olum
    -0.09
    andard
    -0.09
     Cliff
    -0.08
    uled
    -0.08
    SSI
    -0.08
    äºĶæĺŁ
    -0.08
    atan
    -0.08
    chaft
    -0.08
    AGR
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.09
    ãģ»ãģĨ
    0.09
    smith
    0.08
    å¸Ĥ人大
    0.08
    çİĭåĽ½
    0.08
    çĥŃæIJľ
    0.08
    注å®ļ
    0.08
    uration
    0.08
    å²ģæľĪ
    0.08
    çĥŃæ½®
    0.08
    Activations Density 0.017%

    No Known Activations