© 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. 61189
    Prev
    Next
    INDEX
    Explanations

    those using

    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
    ry
    -0.11
    ãģĹãģ¾ãģĦ
    -0.09
    own
    -0.09
     itself
    -0.09
    ter
    -0.09
    è¿Ļ座åŁİå¸Ĥ
    -0.09
     @}
    -0.09
    åĬ²
    -0.09
    ا
    -0.09
    è¿ĻéĩĮæľī
    -0.09
    POSITIVE LOGITS
    /all
    0.12
     pes
    0.11
    venth
    0.11
    zelf
    0.11
    ä¸įåı¯æĢĿ
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.10
    æŶåĢĻ
    0.09
    æĻĤåĢĻ
    0.09
     cazzo
    0.09
    brero
    0.09
    Activations Density 0.043%

    No Known Activations