© 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. 34700
    Prev
    Next
    INDEX
    Explanations

    time to

    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
    è±¢
    -0.09
    æī«ä¸Ģæī«
    -0.09
    تخ
    -0.09
     ob
    -0.09
    ä¸įèĪĴæľį
    -0.09
    å¹³æŶ
    -0.09
    åŁĤ
    -0.09
    ä¸įæĸŃæıIJåįĩ
    -0.09
    ä¸įæĿ¥
    -0.08
    çĤ¬
    -0.08
    POSITIVE LOGITS
     ÑĥÑģп
    0.14
     ká»ĭp
    0.11
    æĿ¥ä¸įåıĬ
    0.11
    zap
    0.10
    赶ä¸Ĭ
    0.10
    æľĢæĸ°
    0.10
    éĤ£æŶ
    0.10
    éĤ£æŶåĢĻ
    0.09
    驱
    0.09
    æľĢæĹ©
    0.09
    Activations Density 0.114%

    No Known Activations