© 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. 49961
    Prev
    Next
    INDEX
    Explanations

    create AR maps

    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
    对人ä½ĵ
    -0.09
    驾
    -0.08
    éļĪ
    -0.08
    æĦıä¹īä¸ĬçļĦ
    -0.08
    aida
    -0.08
    碰
    -0.07
    usting
    -0.07
    ç®Ģ缴
    -0.07
    ä¸ĢåłĨ
    -0.07
    еÑĢÑĤ
    -0.07
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.11
    继ç»Ńä¿ĿæĮģ
    0.10
    cept
    0.09
    ilen
    0.09
    æŃ¤é¡¹
    0.09
    coef
    0.09
    è¿Ļ家ä¼Ļ
    0.09
    è¿Ļ项
    0.09
    çļĦåij½è¿IJ
    0.09
    ä¸ĭ次
    0.09
    Activations Density 0.055%

    No Known Activations