© 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. 27531
    Prev
    Next
    INDEX
    Explanations

    discourage consumption or legal consequences

    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
    æĤĴ
    -0.08
    æĪ½
    -0.08
    igu
    -0.08
    æ°´éĩı
    -0.08
     Cong
    -0.08
    ä¼ijåģĩ
    -0.08
    深度èŀįåIJĪ
    -0.08
    MeasureSpec
    -0.08
    æµģéĩı
    -0.08
     douche
    -0.08
    POSITIVE LOGITS
    ä¿Ŀ管
    0.13
     disposal
    0.11
    æį¡
    0.11
    éĶĢæ¯ģ
    0.11
    æįIJèµł
    0.11
    æīĶ
    0.10
    æĶ¶èĹı
    0.10
    åŃĺæĶ¾
    0.10
    æĶ¶çº³
    0.10
    æĶ¶éĽĨ
    0.10
    Activations Density 0.238%

    No Known Activations