© 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. 1973
    Prev
    Next
    INDEX
    Explanations

    symbols and specific suffixes

    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
    æĿijåħļæĶ¯éĥ¨
    -0.10
    åİ¿å§Ķ
    -0.09
    约è°Ī
    -0.09
    åºľ
    -0.09
    åİ¿å§Ķ书记
    -0.09
    .getBody
    -0.08
    å¸Ĥåľºè§Ħ模
    -0.08
    èĮ§
    -0.08
    åIJ¹
    -0.08
    çĭłçĭł
    -0.08
    POSITIVE LOGITS
    çī©ç§į
    0.12
    åĬ¨çī©
    0.12
    人工
    0.11
    åĬ¨çī©åĽŃ
    0.11
    è§Ĥèµı
    0.10
    (visitor
    0.10
    游客
    0.10
     visitors
    0.10
     visitor
    0.10
    visitor
    0.10
    Activations Density 0.045%

    No Known Activations