© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50558
    Prev
    Next
    INDEX
    Explanations

    invite to visit

    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
    è°ĥåĬ¨
    -0.10
    æĪij没æľī
    -0.09
    åĨ³èĥľ
    -0.09
    ä»ĭ
    -0.09
    天ä¸Ĭ
    -0.09
    åĸľæĤ¦
    -0.09
    离
    -0.08
    解èĦ±
    -0.08
    ç§Łè½¦
    -0.08
    è°Ħ
    -0.08
    POSITIVE LOGITS
    æĭľè®¿
    0.18
    visit
    0.17
     visit
    0.17
    .visit
    0.17
    æĿ¥è®¿
    0.16
    Visit
    0.15
    访
    0.15
     visits
    0.14
     visited
    0.14
     Visit
    0.14
    Activations Density 0.045%

    No Known Activations