© 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. 56955
    Prev
    Next
    INDEX
    Explanations

    colors

    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
    جاÙĦ
    -0.09
    _guide
    -0.08
    ç¬
    -0.08
    æ°ĹãģĮ
    -0.08
    /rc
    -0.08
    å®ĮåĸĦ
    -0.08
    oui
    -0.08
    .Popup
    -0.08
    ampoline
    -0.08
    é£İåı£
    -0.08
    POSITIVE LOGITS
    éľĦ
    0.09
    åīįæıIJæĺ¯
    0.09
    èĪ¬çļĦ
    0.09
    åľ°åĿª
    0.09
    åŃĺéĩı
    0.08
    _ck
    0.08
    ums
    0.08
    æ·»
    0.08
    eners
    0.08
    Ñĥма
    0.08
    Activations Density 0.038%

    No Known Activations