© 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. 3594
    Prev
    Next
    INDEX
    Explanations

    inhibitors and production

    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
    糯米
    -0.10
    PTY
    -0.09
    æ¡£
    -0.09
    ihad
    -0.09
    为ä¹ĭ
    -0.08
    ajs
    -0.08
    ermen
    -0.08
    -gallery
    -0.08
    رÙĬØŃ
    -0.08
    ä¹ĭæīĢ
    -0.08
    POSITIVE LOGITS
    æ®ĭçķĻ
    0.10
    æĿĤ
    0.09
    æ³ķå®ļ代表
    0.09
    åºŁ
    0.09
    åĬŁèĥ½æĢ§
    0.08
    åħļ建
    0.08
    æݧèĤ¡éĽĨåĽ¢
    0.08
    éķ¿çŁŃ
    0.08
    .agent
    0.08
    éĻĨç»Ń
    0.08
    Activations Density 0.204%

    No Known Activations