© 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. 26508
    Prev
    Next
    INDEX
    Explanations

    osteoporosis

    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
    ihan
    -0.09
    è°ĥéħį
    -0.09
    éļ¾å¿ĺ
    -0.09
    TintColor
    -0.09
    mith
    -0.09
    æĿ
    -0.09
    绣
    -0.09
    è¿Ļä¸ĢåĪ»
    -0.08
    åı¶åŃIJ
    -0.08
    ç©
    -0.08
    POSITIVE LOGITS
    çĹĩ
    0.09
    _DL
    0.09
    æ®ĸ
    0.09
    éģĴ
    0.08
    èģĮ
    0.08
    ç©´
    0.08
    iske
    0.08
    åħ±éĿĴåĽ¢
    0.08
    èĢģ人家
    0.08
    sites
    0.08
    Activations Density 0.051%

    No Known Activations