© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35711
    Prev
    Next
    INDEX
    Explanations

    no problems whatsoever

    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
     lest
    -0.10
     ÐĴозможно
    -0.09
    æ¦Ħ
    -0.09
    ä¹Łåı¯èĥ½
    -0.09
    .hp
    -0.09
    åı¯èĥ½åŃĺåľ¨
    -0.09
    箧
    -0.09
    ç»Ī
    -0.08
    è¦ģåѦä¼ļ
    -0.08
    åIJ¦
    -0.08
    POSITIVE LOGITS
    POSE
    0.10
    æ·±åĮĸæĶ¹éĿ©
    0.10
     EVER
    0.10
    ä»İæĿ¥æ²¡
    0.10
    ä»İæľª
    0.09
    表çİ°åĩº
    0.09
     bisher
    0.09
    æĪªèĩ³çĽ®åīį
    0.09
    æľīä»»ä½ķ
    0.09
    éĩį大
    0.08
    Activations Density 0.067%

    No Known Activations