© 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. 9567
    Prev
    Next
    INDEX
    Explanations

    list of

    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
    大åıĶ
    -0.08
     ÄijÃło
    -0.08
    åĽŀé¦ĸ
    -0.08
    à¹Ģหà¸Ļ
    -0.08
    ìĦ¸
    -0.08
    .ud
    -0.08
    ucher
    -0.08
    Ford
    -0.08
    ä¸Ģåı°
    -0.08
    isher
    -0.08
    POSITIVE LOGITS
    åIJįåįķ
    0.11
    æ¸ħåįķ
    0.11
     list
    0.10
     lists
    0.10
    交ç»Ļ
    0.10
    åĩºåİĤ
    0.09
    rik
    0.09
    ä¸įä¸ĭ
    0.09
    enable
    0.09
    ä¸Ĭæľī
    0.09
    Activations Density 0.087%

    No Known Activations