© 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. 6046
    Prev
    Next
    INDEX
    Explanations

    distance measurements

    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
    rokes
    -0.10
    ãģĵãģĿ
    -0.09
    สล
    -0.09
    elor
    -0.09
    éªĩ
    -0.09
     Apprentice
    -0.09
    车载
    -0.09
     Gaut
    -0.09
    é«ĺä½į
    -0.09
    éªŀ
    -0.09
    POSITIVE LOGITS
    è·Ŀ离
    0.13
    çļĦè·Ŀ离
    0.12
     distance
    0.11
    è·ĿéĽ¢
    0.11
    ors
    0.09
     Distance
    0.09
     distances
    0.09
    .distance
    0.09
    _distance
    0.09
    distance
    0.09
    Activations Density 0.025%

    No Known Activations