© 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. 56586
    Prev
    Next
    INDEX
    Explanations

    musical notes and scales

    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
    æ½
    -0.09
    åħģ
    -0.09
    éľŃ
    -0.09
    ä¸įåIJ«
    -0.09
    è±ķ
    -0.09
    еÑĪ
    -0.09
    棵æłij
    -0.09
     Gingrich
    -0.09
    å§IJ
    -0.09
    åı£æ°´
    -0.08
    POSITIVE LOGITS
    ĥĿ
    0.09
    spiel
    0.09
    èĭ¦
    0.08
    è¦ĨçĽĸçİĩ
    0.08
    Ju
    0.08
    çĨ¬
    0.08
    峡谷
    0.08
    èĮ§
    0.08
    ytt
    0.08
    /std
    0.08
    Activations Density 0.029%

    No Known Activations