© 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. 47940
    Prev
    Next
    INDEX
    Explanations

    media related 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
    访
    -0.09
    æĶ¶å½ķ
    -0.08
    azing
    -0.08
    engo
    -0.08
    æĶ¯ä»ĺå®Ŀ
    -0.08
    arding
    -0.08
    èħĬ
    -0.08
    ãģĦãĤĦ
    -0.08
    alth
    -0.08
    ÑĢÑĥ
    -0.08
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.09
    ä¸į足
    0.09
    åĴĮ社ä¼ļ
    0.09
    仪表
    0.08
    (Media
    0.08
    ç§ĭ
    0.08
    ãģ¡ãģ¯
    0.08
    èĵŁ
    0.08
    æĬķèµĦé¢Ŀ
    0.08
     instant
    0.08
    Activations Density 0.026%

    No Known Activations