© 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. 3427
    Prev
    Next
    INDEX
    Explanations

    questions asking what or which

    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
    èݽ
    -0.09
    æĿ¨
    -0.08
     El
    -0.07
    æ¯į
    -0.07
    æ¥Ĭ
    -0.07
    lef
    -0.07
    éĻ¤éĿŀ
    -0.07
    æѧ
    -0.07
    El
    -0.07
     said
    -0.07
    POSITIVE LOGITS
     yourselves
    0.11
    座è°Ī
    0.11
    ENCED
    0.10
    欢è¿İ大家
    0.10
     какие
    0.09
    ä½łèĩªå·±
    0.09
    å¡«åĨĻ
    0.09
    imes
    0.09
    究竣æĺ¯
    0.09
     ØŃر
    0.09
    Activations Density 0.051%

    No Known Activations