© 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. 48771
    Prev
    Next
    INDEX
    Explanations

    accept or decline

    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
    æ¯ıä½į
    -0.10
    çĹī
    -0.10
    åį¸
    -0.10
    æģ¨
    -0.09
    å¦Ĵ
    -0.09
     Cel
    -0.09
     cel
    -0.09
     Celt
    -0.09
    个åĪ«
    -0.09
     CEL
    -0.08
    POSITIVE LOGITS
    常年
    0.09
    åı¯æĥ³
    0.09
     Furious
    0.08
    oner
    0.08
    isplay
    0.08
    ç¨İåĬ¡æĢ»å±Ģ
    0.08
    æŀ¶åŃIJ
    0.08
    ç»Łè®¡å±Ģ
    0.08
    inal
    0.08
    ç¥
    0.08
    Activations Density 0.026%

    No Known Activations