© 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. 50304
    Prev
    Next
    INDEX
    Explanations

    war or variable occurrences

    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
    orio
    -0.09
    eger
    -0.09
    å¸
    -0.09
    ëıĮ
    -0.09
    éĥ¨å§Ķ
    -0.09
    _singleton
    -0.09
    obb
    -0.09
    ozo
    -0.08
    èĩ´
    -0.08
    ovation
    -0.08
    POSITIVE LOGITS
    fel
    0.09
    ä¸į让
    0.09
     Ale
    0.08
    éĥ¿
    0.08
    è´Ŀ壳
    0.08
    æį¢
    0.08
    bases
    0.08
     createStore
    0.08
    è´¢ç»ı
    0.08
    人æ°ij
    0.08
    Activations Density 0.060%

    No Known Activations