© 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. 24107
    Prev
    Next
    INDEX
    Explanations

    bet you

    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
    èĩªåıij
    -0.08
    usk
    -0.08
    大èĩ´
    -0.08
    踵
    -0.08
    é¢Ħå¤ĩ
    -0.08
    èĪįå¾Ĺ
    -0.08
    亿ä¸ĩ
    -0.08
    ä¸ĸ家
    -0.08
     Nicole
    -0.08
    .wh
    -0.08
    POSITIVE LOGITS
    ted
    0.11
    ters
    0.10
    èĬĻèĵī
    0.10
    ä¸įæİĴéĻ¤
    0.09
    åĵī
    0.09
    clar
    0.09
    adic
    0.09
    æİ°
    0.09
    /be
    0.09
    aire
    0.09
    Activations Density 0.004%

    No Known Activations