© 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. 63202
    Prev
    Next
    INDEX
    Explanations

    existence or occurrence

    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
    åıįèĢĮ
    -0.09
    享çĶ¨
    -0.09
    æľīä»Ģä¹Ī
    -0.09
    æĭ´
    -0.09
     бÑĥкв
    -0.08
    æģ
    -0.08
    è¿ĺæľīä»Ģä¹Ī
    -0.08
    оде
    -0.08
    .wh
    -0.08
     sor
    -0.08
    POSITIVE LOGITS
    ä½Ĩ
    0.11
    ãģ¯ãģĤãĤĭ
    0.11
     but
    0.11
    ä½Ĩä¸įéĻIJäºİ
    0.10
    ä½Ĩä»İ
    0.10
    but
    0.10
    ä½Ĩä»ĸ们
    0.10
    ä½Ĩåį´
    0.09
    大æ£ļ
    0.09
    ä¸Ķ
    0.09
    Activations Density 0.290%

    No Known Activations