© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9956
    Prev
    Next
    INDEX
    Explanations

    with a

    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
    çľĭä¸įåĩº
    -0.09
    mares
    -0.09
    /history
    -0.09
    untime
    -0.08
    èµ°åľ¨
    -0.08
    ANCES
    -0.08
    èĤĩ
    -0.08
    èĢĮæĺ¯
    -0.08
    èªī
    -0.08
     hs
    -0.08
    POSITIVE LOGITS
    ä¿¡å¿ĥ
    0.12
    çĥŃæĥħ
    0.11
    æľīä¿¡å¿ĥ
    0.09
    å°Ĭ严
    0.09
    èī¯
    0.09
    èĻļ
    0.09
    åįģ足
    0.09
    è¯ļæĦı
    0.09
    æ¸ħéĨĴ
    0.09
    æĮģä¹ħ
    0.08
    Activations Density 0.053%

    No Known Activations