© 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. 33104
    Prev
    Next
    INDEX
    Explanations

    volumes, series, episodes

    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
    å¤ļç§į
    -0.09
    èĢĥåľº
    -0.09
    IgnoreCase
    -0.09
    åı¬
    -0.08
    å¤ļ项
    -0.08
     cage
    -0.08
    åIJĽåŃIJ
    -0.08
     Hoff
    -0.08
     Hoffman
    -0.08
    åIJĦè¡ĮåIJĦä¸ļ
    -0.08
    POSITIVE LOGITS
    åIJİç»Ń
    0.11
     volumes
    0.10
    ç³»åĪĹ
    0.10
    å®Įç»ĵ
    0.10
    åī©ä¸ĭ
    0.10
    å§Ĭ妹
    0.10
    ä¸ĢæľŁ
    0.10
     titles
    0.09
     episodes
    0.09
     stages
    0.09
    Activations Density 0.117%

    No Known Activations