© 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. 59081
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    丰ç¡ķ
    -0.08
    éĻĮçĶŁ
    -0.08
    _U
    -0.08
    aisy
    -0.08
    åºĦåĽŃ
    -0.08
    etto
    -0.08
    åIJĪçIJĨ
    -0.08
    æł¡
    -0.08
    åĪĽä½ľ
    -0.08
    malink
    -0.08
    POSITIVE LOGITS
    主æĮģ
    0.17
    主æĮģ人
    0.15
    解说
    0.10
    å¨ĵ
    0.10
    å¥ĸ
    0.10
    åĸĭ
    0.09
    åĸī
    0.09
    èģĴ
    0.09
    åĬ©
    0.09
    arb
    0.09
    Activations Density 0.086%

    No Known Activations