© 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. 10334
    Prev
    Next
    INDEX
    Explanations

    punishable offence

    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
    骤
    -0.09
    æŁ¥å°ģ
    -0.09
    诡
    -0.09
    çªģå¦Ĥåħ¶
    -0.09
    ä¸Ģéĺµ
    -0.09
    寡
    -0.09
    æĺĻ
    -0.09
    åī¯ä¸»å¸Ń
    -0.09
    ä¸Ģæ³¢
    -0.09
    åIJį家
    -0.08
    POSITIVE LOGITS
    æIJŃ
    0.10
    罪
    0.10
     punishable
    0.10
     offenses
    0.09
    åĪijäºĭ责任
    0.09
    èĪĢ
    0.08
    è½»
    0.08
    æ·¡åĮĸ
    0.08
     possession
    0.08
     undefined
    0.08
    Activations Density 0.205%

    No Known Activations