© 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. 59033
    Prev
    Next
    INDEX
    Explanations

    phones and displays

    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
    éĿ¶
    -0.10
     Fab
    -0.09
    æ¶īå«Į
    -0.09
    æİĮ
    -0.08
    éħ£
    -0.08
     Hou
    -0.08
     fab
    -0.08
    è¿Ļå¥Ĺ
    -0.08
     Volume
    -0.08
     bow
    -0.08
    POSITIVE LOGITS
    亲
    0.11
    éĩįçĤ¹åħ³æ³¨
    0.09
    .har
    0.09
    uess
    0.09
    звон
    0.09
    styl
    0.08
    çķ´
    0.08
    åŀŃ
    0.08
    æ½®
    0.08
    çķĻä¸ĭæĿ¥
    0.08
    Activations Density 0.146%

    No Known Activations