© 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. 11744
    Prev
    Next
    INDEX
    Explanations

    colors and descriptions

    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
    ç´¯
    -0.10
    å¤ĸ交
    -0.09
    积
    -0.09
    ä¾Ŀ
    -0.09
    ç©į
    -0.08
    约æĿŁ
    -0.08
    åĿ
    -0.08
     Holl
    -0.08
    æĶ¹åĪ¶
    -0.08
    wrapped
    -0.08
    POSITIVE LOGITS
    èī³
    0.10
    è¿ĺåİŁ
    0.09
    é¢ľèī²
    0.09
     colors
    0.09
    æ·ĭ
    0.09
    é²ľæĺİ
    0.09
    é²ľèī³
    0.09
    é£Łæ¬²
    0.09
    uat
    0.09
    èī²å½©
    0.09
    Activations Density 0.068%

    No Known Activations