© 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. 39360
    Prev
    Next
    INDEX
    Explanations

    time.sleep

    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
    ยะ
    -0.08
    Č
    -0.08
    rev
    -0.08
    绿èĮ¶
    -0.08
    åĵĪåĵĪ
    -0.08
    inish
    -0.08
    Assembler
    -0.08
     Wit
    -0.07
    èĦ¯
    -0.07
    ä¸ĭæ²ī
    -0.07
    POSITIVE LOGITS
    ÑĦон
    0.12
    æݨèįIJéĺħ读
    0.10
    çű
    0.10
    ä¸Ģæľµ
    0.10
    èº
    0.10
    ä¸į代表
    0.10
    nox
    0.09
     ÑĦон
    0.09
    ä¸Ģéģĵ
    0.09
    èŁ¹
    0.09
    Activations Density 0.002%

    No Known Activations