© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36235
    Prev
    Next
    INDEX
    Explanations

    to alter or permit

    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
    ç»´æĬ¤
    -0.08
    .utf
    -0.08
    åľ¨å®¶
    -0.08
    heim
    -0.08
    asco
    -0.08
    ÙħÙĨتدÙī
    -0.08
     fri
    -0.08
    andin
    -0.07
    abar
    -0.07
     Fantastic
    -0.07
    POSITIVE LOGITS
    赶
    0.11
    æı©
    0.10
    æ¯ķ
    0.10
    æĸ°ä¸ī
    0.09
    itial
    0.09
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    èĭ´
    0.09
    iliation
    0.08
    æĶ¸
    0.08
    箪
    0.08
    Activations Density 0.183%

    No Known Activations