© 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. 11141
    Prev
    Next
    INDEX
    Explanations

    messenger, pawn, drone, hired, leading

    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
    äºĭåħ³
    -0.10
    wner
    -0.10
    å¥ĭæĸĹ缮æłĩ
    -0.09
    éļ¾æ°ij
    -0.09
    æ¿ĢçĥĪçļĦ
    -0.08
    ç»ĦåĽ¢
    -0.08
    èĩªåľ¨
    -0.08
    æ¾İæ¹ĥ
    -0.08
    ç»Ħ
    -0.08
    greens
    -0.08
    POSITIVE LOGITS
    代è¨Ģ人
    0.15
    代çIJĨ人
    0.15
    åĬ©æīĭ
    0.11
    人éĢī
    0.10
    为代表
    0.10
    ä¼łéĢĴ
    0.10
    é£İæ°´
    0.10
    åıijè¨Ģ人
    0.09
    代è¨Ģ
    0.09
    ãĥ¡ãĥĥ
    0.09
    Activations Density 0.078%

    No Known Activations