© 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. 48898
    Prev
    Next
    INDEX
    Explanations

    dosage and interval schedule

    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
    æĺ¯æľĢ好çļĦ
    -0.11
    åĢ¦
    -0.10
    路人
    -0.10
    快讯
    -0.09
    好人
    -0.09
    æĴŃæĬ¥
    -0.09
    åĬ£åĬ¿
    -0.09
    è¿ĩå¾Ĺ
    -0.09
    TT
    -0.09
    iron
    -0.08
    POSITIVE LOGITS
    (pointer
    0.09
    访éĹ®
    0.09
    .converter
    0.09
    ÑīÑĥ
    0.09
    åĿĢ
    0.09
    ìĪĻ
    0.08
     swinger
    0.08
    åĩĨ
    0.08
    彧
    0.08
    BUM
    0.08
    Activations Density 0.019%

    No Known Activations