© 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. 40036
    Prev
    Next
    INDEX
    Explanations

    typepad.com distribution

    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
    ÑģÑĤÑĢа
    -0.10
    vero
    -0.08
    DED
    -0.08
    åıĪ被
    -0.08
    æºľ
    -0.08
    çĶŁçī©åѦ
    -0.08
    ITT
    -0.08
     Tomorrow
    -0.08
    è¦ģ害
    -0.08
    æī«
    -0.08
    POSITIVE LOGITS
    翻身
    0.10
    .getRaw
    0.09
    ROUGH
    0.08
    çħ§
    0.08
    erus
    0.08
     Robbins
    0.08
    .setViewport
    0.08
    APO
    0.08
    æģŃ
    0.08
    çļĦåľ°æŃ¥
    0.08
    Activations Density 0.004%

    No Known Activations