© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34145
    Prev
    Next
    INDEX
    Explanations

    with ... in mind

    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
    æªĢ
    -0.09
    åŃĺåľ¨äºİ
    -0.09
    ä¸įä¼ļæľī
    -0.09
    çĥģ
    -0.09
    åĸľ
    -0.09
    ä¸Ńæľī
    -0.09
    IRA
    -0.08
    èĩªåĪĨãģĮ
    -0.08
    ä¸Ģä¸ĭ
    -0.08
    严éĩįå½±åĵį
    -0.08
    POSITIVE LOGITS
    æĬ¤çħ§
    0.10
    éĵł
    0.10
    engo
    0.10
    rary
    0.09
    éģĴ
    0.09
    訾
    0.09
    го
    0.09
    ç½®
    0.09
    .buf
    0.09
     <<"
    0.09
    Activations Density 0.013%

    No Known Activations