© 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. 35782
    Prev
    Next
    INDEX
    Explanations

    legal case parties

    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
    çļĦéĴ±
    -0.10
    ä¸Ģç±»
    -0.10
    éĥ¨ä¸»ä»»
    -0.09
    å¥
    -0.09
    å¼Ģåĩº
    -0.09
    ฯ
    -0.09
    akk
    -0.09
    éĵºè®¾
    -0.09
    èµ°åľ¨
    -0.09
    IsNull
    -0.09
    POSITIVE LOGITS
    æĿĤå¿Ĺ社
    0.11
    åŁ¹è®ŃæľºæŀĦ
    0.11
    å¾ĭå¸ĪäºĭåĬ¡
    0.10
    æĵ¢
    0.09
    ìķ¤
    0.09
    ä¼ģä¸ļåıijå±ķ
    0.09
    该åħ¬åı¸
    0.09
    åħīæºIJ
    0.08
    Ùħباد
    0.08
    ä¸Ĭå¸Ĥåħ¬åı¸
    0.08
    Activations Density 0.570%

    No Known Activations