© 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. 57759
    Prev
    Next
    INDEX
    Explanations

    abstract states and qualities

    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
    æ¶ī
    -0.10
    嶷
    -0.10
    æķķ
    -0.10
     ÑħозÑı
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    èµī
    -0.09
    è¿ĩåī©
    -0.09
    çľĭä¸įåĩº
    -0.08
    è¿Ľè´§
    -0.08
    çĮĸ
    -0.08
    POSITIVE LOGITS
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.10
    çŁ¥éģĵèĩªå·±
    0.10
    sta
    0.08
     của
    0.08
     of
    0.08
     Pri
    0.08
     Stations
    0.08
     unst
    0.08
    èļ¤
    0.08
    pri
    0.07
    Activations Density 0.121%

    No Known Activations