© 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. 4915
    Prev
    Next
    INDEX
    Explanations

    neural circuits and brain regions

    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
    æĬ½
    -0.11
     tre
    -0.09
    elves
    -0.09
     PED
    -0.09
    ubby
    -0.09
    认åIJĮ
    -0.08
    arend
    -0.08
    tre
    -0.08
    ightly
    -0.08
    boats
    -0.08
    POSITIVE LOGITS
    .hot
    0.10
    èĩªå¾ĭ
    0.09
    æĥħåķĨ
    0.09
    åħ¨èĩªåĬ¨
    0.09
    ä¸Ģ大æī¹
    0.09
    鸣
    0.09
    ä½ŀ
    0.09
    åĪį
    0.09
    ä¸Ģè§Ī
    0.09
    太å°ij
    0.09
    Activations Density 0.357%

    No Known Activations