© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40274
    Prev
    Next
    INDEX
    Explanations

    head coach

    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
    Negative Logits
    иÑĤеÑģÑĮ
    -0.09
    ä¸Ī
    -0.09
    ãĢħ
    -0.09
    otomy
    -0.09
    webkit
    -0.08
    ãģ¤ãģ¤
    -0.08
    gons
    -0.08
    engers
    -0.08
    iras
    -0.08
    queen
    -0.08
    POSITIVE LOGITS
    Buzz
    0.09
    رة
    0.09
    éĤ
    0.08
    erald
    0.08
    /her
    0.08
     mich
    0.08
    (separator
    0.08
    æīĭä¸ŃçļĦ
    0.08
    å¥Ĺè£ħ
    0.08
    sr
    0.08
    Activations Density 0.007%

    No Known Activations