© 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. 4684
    Prev
    Next
    INDEX
    Explanations

    solutions and related contexts

    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
    æŶéĹ´åĴĮ
    -0.09
    dar
    -0.09
    æĹģ
    -0.08
     ÑģовеÑĢÑĪен
    -0.08
    tab
    -0.08
    iod
    -0.08
    åģļ人
    -0.08
    editor
    -0.08
    enna
    -0.07
     british
    -0.07
    POSITIVE LOGITS
    æıIJä¾ĽåķĨ
    0.13
    arily
    0.11
    èĢģåħµ
    0.10
    aries
    0.10
    巨头
    0.09
    ï¸
    0.09
    髯
    0.09
    主ä¹īèĢħ
    0.09
    å¿¿
    0.09
     обÑĭ
    0.09
    Activations Density 0.018%

    No Known Activations