© 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. 18423
    Prev
    Next
    INDEX
    Explanations

    carbon fiber

    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
    enes
    -0.09
    æ¢Ń
    -0.09
    .tex
    -0.09
    纺
    -0.08
    ican
    -0.08
    ogn
    -0.08
    ume
    -0.08
    æĹĭ
    -0.08
    é«ĺæ°´å¹³
    -0.08
    ç»ĩ
    -0.08
    POSITIVE LOGITS
    ç²īæľ«
    0.10
    åĴİ
    0.09
    åĿĹ
    0.09
    åĮħè£ħ
    0.09
     Wick
    0.09
    åŀĴ
    0.09
    ä¸ĢåĿĹ
    0.09
    ä¹Ķ
    0.09
    ULO
    0.09
    ä¸ĢæĶ¯
    0.09
    Activations Density 0.070%

    No Known Activations