© 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. 39935
    Prev
    Next
    INDEX
    Explanations

    no smoking, free, welcome, beverages

    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
    è¿·
    -0.09
     Scar
    -0.09
    å«ģç»Ļ
    -0.08
    .DriverManager
    -0.08
    æ´»
    -0.08
    éĽį
    -0.08
    夫
    -0.08
    æĬ¥åºŁ
    -0.08
    otas
    -0.08
    çķ¥
    -0.08
    POSITIVE LOGITS
    ä½ľé£İ
    0.09
    OOT
    0.09
     vict
    0.08
    åľ¨ä¸Ģ个
    0.08
    åħ±åĴĮ
    0.08
    ä¸Ģç»ı
    0.08
    zn
    0.08
     tÃŃn
    0.08
    irt
    0.08
    /tiny
    0.08
    Activations Density 0.014%

    No Known Activations