© 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. 23871
    Prev
    Next
    INDEX
    Explanations

    or implied warranties

    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
    对ç«ĭ
    -0.09
    ĪæĿĥ
    -0.09
    usic
    -0.09
    utter
    -0.08
     trainers
    -0.08
    åĽ½ç±į
    -0.08
    æĽ´åĬł
    -0.08
     hypothetical
    -0.08
     bian
    -0.08
     Moff
    -0.08
    POSITIVE LOGITS
    Naming
    0.10
    ä½³
    0.10
    ilton
    0.09
    è¨Ģ
    0.09
    ä¹ĭ家
    0.09
    ç³Ļ
    0.09
    éĻ¢å£«
    0.09
    æĺ¥åŃ£
    0.09
    æ´Ľåħĭ
    0.08
    çijľ
    0.08
    Activations Density 0.092%

    No Known Activations