© 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. 35662
    Prev
    Next
    INDEX
    Explanations

    call today

    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
    ä¸Ģ带
    -0.10
    æģ¯
    -0.09
    ä¸ī天
    -0.09
    SOR
    -0.09
    æĺĵäºİ
    -0.09
    严åİīæīĵåĩ»
    -0.09
    ä¸Ģ大æĹ©
    -0.09
    .inline
    -0.08
    æ°ı
    -0.08
    丸
    -0.08
    POSITIVE LOGITS
    åıªè¦ģæĺ¯
    0.10
    pent
    0.09
    hone
    0.09
    омеÑĢ
    0.09
    åıªè¦ģä½ł
    0.09
    eties
    0.09
    èŃ
    0.09
    èģĶç³»
    0.08
     opr
    0.08
    ä¸ĭ次
    0.08
    Activations Density 0.003%

    No Known Activations