© 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. 6738
    Prev
    Next
    INDEX
    Explanations

    activity 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
    åīij
    -0.09
    velt
    -0.09
    çĥŃè¡Ģ
    -0.08
    ploy
    -0.08
    èĦ¯
    -0.08
    è¯ķè¯ķ
    -0.08
    ãģĦãģ£ãģŁ
    -0.08
    аÑĢаÑĤ
    -0.08
    ç¬ĥ
    -0.08
    æ´ĭèij±
    -0.08
    POSITIVE LOGITS
    reich
    0.11
    INGS
    0.10
    erts
    0.09
    åĻ¨æĿIJ
    0.09
    rias
    0.09
    æİ¢æµĭ
    0.09
    é¹Ĭ
    0.09
    ink
    0.09
    åįģ足
    0.08
    æĿijéķĩ
    0.08
    Activations Density 0.045%

    No Known Activations