© 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. 6555
    Prev
    Next
    INDEX
    Explanations

    Formula 1 names and locations

    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
    è½±
    -0.11
    åŁ´
    -0.09
    迺
    -0.09
    æĬ¥åijĬæľŁåĨħ
    -0.09
    羣å®ŀæĢ§
    -0.09
    åIJĦè¡Į
    -0.08
    æľ¬æĬ¥è®°èĢħ
    -0.08
    åįĹå®ģå¸Ĥ
    -0.08
    屯
    -0.08
    奶
    -0.08
    POSITIVE LOGITS
    ä¸Ģ线
    0.11
    æij
    0.08
    erin
    0.08
    è¿ĻæĶ¯
    0.08
    ort
    0.08
    mpr
    0.08
    èĬ±çĵ£
    0.08
    ạt
    0.08
    WithOptions
    0.08
    è¯¾æľ¬
    0.08
    Activations Density 0.016%

    No Known Activations