© 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. 54268
    Prev
    Next
    INDEX
    Explanations

    intellectualism and intellect

    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
    å°¼æĸ¯
    -0.09
    åij
    -0.09
    åŁ¹
    -0.08
    สา
    -0.08
    lag
    -0.08
    æĮĩå°ĸ
    -0.08
    纫
    -0.08
    à°³
    -0.08
    åIJīåĪ©
    -0.08
    رÙĪب
    -0.08
    POSITIVE LOGITS
    éĻ¢éķ¿
    0.12
    lectual
    0.11
    éĻ¢éĻ¢éķ¿
    0.11
    对æīĭ
    0.09
    ç²¾èĭ±
    0.09
    åī¯éĻ¢éķ¿
    0.09
    legg
    0.08
    çŁ¥è¯ĨåĪĨåŃIJ
    0.08
    头æĿ¡
    0.08
    ercial
    0.08
    Activations Density 0.028%

    No Known Activations