© 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. 48288
    Prev
    Next
    INDEX
    Explanations

    University professor English literature

    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
    åĺĺ
    -0.10
    ä¸Ńæĸĩ
    -0.09
    æ£ł
    -0.09
    éģĤ
    -0.09
    ä¸Ģç¬ij
    -0.09
    èĢĥè¯ģ
    -0.09
    hall
    -0.09
    Trivia
    -0.08
    线索
    -0.08
    verse
    -0.08
    POSITIVE LOGITS
    çłº
    0.09
    LIN
    0.09
    åĨĻä½ľ
    0.09
    è¯Ńæĸĩ
    0.09
    еÑģÑĤи
    0.09
    笺
    0.08
    nearest
    0.08
    _dense
    0.08
    ä¸Ģ个æĺŁæľŁ
    0.08
     Pound
    0.08
    Activations Density 0.072%

    No Known Activations