© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20133
    Prev
    Next
    INDEX
    Explanations

    people committing crime

    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
    å¾Ĺ罪
    -0.10
    æ¡£
    -0.10
    æĺ¥ç§ĭ
    -0.09
    æªĶ
    -0.09
    .office
    -0.09
    å¿ĥè¡Ģ
    -0.09
    athe
    -0.09
    éĿ¡
    -0.08
    åIJĦ家
    -0.08
    .Mutable
    -0.08
    POSITIVE LOGITS
    æľªçŁ¥
    0.11
    æİıåĩº
    0.09
    åıµ
    0.09
    æıª
    0.09
    .UNKNOWN
    0.09
    éĻĮçĶŁ
    0.09
    çļĦ身份
    0.08
    身份
    0.08
     unknown
    0.08
    ory
    0.08
    Activations Density 0.050%

    No Known Activations