© 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. 7613
    Prev
    Next
    INDEX
    Explanations

    copyright and license terms

    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
    骤
    -0.09
    è¥Ħ
    -0.08
    ä»ħä¾ĽåıĤèĢĥ
    -0.07
    åĺ¿
    -0.07
     arc
    -0.07
     Sed
    -0.07
    æ¨Ĭ
    -0.07
    å¸ĮæľĽèĥ½
    -0.07
    lock
    -0.07
    arc
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    osos
    0.09
    osas
    0.09
    å¿ħéľĢ
    0.09
    ROTO
    0.09
    OTE
    0.09
    roe
    0.09
    stag
    0.09
    ellig
    0.09
    ecess
    0.09
    Activations Density 0.031%

    No Known Activations