© 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. 32309
    Prev
    Next
    INDEX
    Explanations

    describing actions or conduct

    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»ıèIJ¥èĮĥåĽ´
    -0.10
    妥åįı
    -0.10
    ç»ıè¿ĩå¤ļå¹´
    -0.10
    æµĵéĥģ
    -0.09
    æ³³
    -0.09
    æĸ°ä¸ī
    -0.09
     iota
    -0.09
    _arrays
    -0.09
    ussion
    -0.08
    åı¸
    -0.08
    POSITIVE LOGITS
    èĻIJ
    0.10
    æĢģ度
    0.09
    çļĦåģļæ³ķ
    0.09
    го
    0.09
    ãģªãģıãģ¦ãĤĤ
    0.09
     acts
    0.09
    ãĤŃãĥ³
    0.09
    åĩºç§Ł
    0.09
     Acts
    0.08
    å¤Ħå¤Ħ
    0.08
    Activations Density 0.071%

    No Known Activations