© 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. 40289
    Prev
    Next
    INDEX
    Explanations

    Inter related words

    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
    ãģ»ãģĨ
    -0.10
    è´´
    -0.10
    æįº
    -0.09
     trÃŃ
    -0.09
    etime
    -0.09
    éĢĿ
    -0.09
    -0.08
    gether
    -0.08
    ÑıÑĤ
    -0.08
    .stat
    -0.08
    POSITIVE LOGITS
    (inter
    0.11
    polation
    0.10
    edly
    0.10
    ingly
    0.10
    stitial
    0.09
    usion
    0.09
    EDIATE
    0.09
    ible
    0.09
    calar
    0.09
    è°į
    0.09
    Activations Density 0.114%

    No Known Activations