© 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. 56647
    Prev
    Next
    INDEX
    Explanations

    I want / we want / I need

    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
    æĶ¾è¿Ľ
    -0.08
    _Arg
    -0.08
    3
    -0.07
    åĵĦ
    -0.07
     dp
    -0.07
    1
    -0.07
    ä¸įéĻIJ
    -0.07
    ëŀĢ
    -0.07
    yst
    -0.07
    cha
    -0.07
    POSITIVE LOGITS
    æ¯ıä¸Ģä½į
    0.12
    å¸ĮæľĽå¤§å®¶
    0.12
    åħ¨ä½ĵåijĺå·¥
    0.11
    ç»Ļ大家
    0.11
    å½ĵéĢī
    0.10
    è¿Ļä¸ĢåĪ»
    0.10
    æĸ°çļĦä¸Ģ
    0.10
    è°¨
    0.10
    ç»Ļä½łä»¬
    0.10
    èĩ´è¾ŀ
    0.10
    Activations Density 0.072%

    No Known Activations