© 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. 48651
    Prev
    Next
    INDEX
    Explanations

    win or loss results

    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
    è§Ħ模æľĢ大
    -0.12
    å¼ķæĵİ
    -0.10
    æĪķ
    -0.10
    ãĤĤãģ£ãģ¨
    -0.10
    _VIRTUAL
    -0.10
    ëħ¼
    -0.09
    妪
    -0.09
    缴å±ŀ
    -0.09
    èµ·æĿ¥
    -0.09
    é£İéĩĩ
    -0.09
    POSITIVE LOGITS
    åĨ³ä¸į
    0.09
    æĮ½
    0.09
    éľ²åĩº
    0.08
    æī³
    0.08
    CurrentValue
    0.08
     Enlight
    0.08
    anc
    0.07
    èĢģ家
    0.07
    reve
    0.07
     ph
    0.07
    Activations Density 0.054%

    No Known Activations