© 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. 29999
    Prev
    Next
    INDEX
    Explanations

    names of inventors and historical figures

    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
    ermann
    -0.09
    é«ĺåİŁ
    -0.09
     единÑģÑĤв
    -0.08
    åīįæīĢæľªæľī
    -0.08
    uman
    -0.08
    OX
    -0.08
     FAG
    -0.08
    opp
    -0.08
    agement
    -0.08
    OptionsMenu
    -0.08
    POSITIVE LOGITS
    ÙĬØ¡
    0.10
    她说
    0.10
    åijĻ
    0.09
    çĥ¨
    0.09
    æ²»æĦĪ
    0.09
    ä»ĸ表示
    0.09
    æĹ¥æĬ¥è®°èĢħ
    0.09
    ä»ĸ说
    0.09
     Edison
    0.09
    åĩºéĻ¢
    0.09
    Activations Density 0.005%

    No Known Activations