© 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. 31846
    Prev
    Next
    INDEX
    Explanations

    you must be

    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
    ä¸Ģç¢Ĺ
    -0.09
    ret
    -0.09
    URN
    -0.09
    oni
    -0.09
    ettle
    -0.09
    oble
    -0.08
    _UNIQUE
    -0.08
    çĦ¼
    -0.08
    onom
    -0.08
    好象
    -0.08
    POSITIVE LOGITS
    ç´¯äºĨ
    0.09
    .ReadLine
    0.09
    zeÅĽ
    0.09
    äº¤æĽ¿
    0.08
    ļĮ
    0.08
    .Builder
    0.08
    èĵŁ
    0.08
    igest
    0.08
    æĸĩåĮĸ建设
    0.08
     Bund
    0.08
    Activations Density 0.002%

    No Known Activations