© 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. 52590
    Prev
    Next
    INDEX
    Explanations

    act quickly, action, create action

    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
    hoe
    -0.11
    鬻
    -0.09
    èĵ¬
    -0.09
    PLE
    -0.09
     Gór
    -0.09
    æ³ķåħ°
    -0.09
    客
    -0.08
    çļĦ好
    -0.08
     reception
    -0.08
     lá»ĩ
    -0.08
    POSITIVE LOGITS
    è¡ĮåĬ¨
    0.15
    ä¸ĭæīĭ
    0.14
     action
    0.14
    è¡Įåĭķ
    0.13
    .Action
    0.12
     Action
    0.12
    Action
    0.12
     createAction
    0.11
    æŀľæĸŃ
    0.11
    éĩĩåıĸ
    0.11
    Activations Density 0.037%

    No Known Activations