© 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. 30455
    Prev
    Next
    INDEX
    Explanations

    sender information: from: to:

    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
    è®·
    -0.09
    å°±åı¯ä»¥äºĨ
    -0.08
    å¼Ħ
    -0.08
    ä¸Ģ段
    -0.08
    amp
    -0.08
    åĪ°æľŁ
    -0.08
    纳æĸ¯
    -0.08
    å¥İ
    -0.08
    tw
    -0.07
    atter
    -0.07
    POSITIVE LOGITS
    :
    0.12
    ï¼ļ
    0.12
    ï¼ļ<
    0.09
    wort
    0.09
    lick
    0.09
    éĥģ
    0.09
    èĥľä»»
    0.08
    åŁİå¢Ļ
    0.08
    éĵĤ
    0.08
     Jub
    0.08
    Activations Density 0.339%

    No Known Activations