© 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. 55414
    Prev
    Next
    INDEX
    Explanations

    allow or permit

    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
    å°ıå¾®
    -0.10
    mention
    -0.10
    5
    -0.09
    å¾®å¦Ļ
    -0.09
    æģ¯
    -0.09
    对该
    -0.09
    æĪijå·²ç»ı
    -0.09
    iff
    -0.08
    aday
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    locking
    0.11
    æ»ĭ
    0.11
    _trampoline
    0.10
    èį¼
    0.10
    SION
    0.10
    UBL
    0.10
    鸳
    0.10
    äºĨèĩªå·±çļĦ
    0.09
    æ¢ı
    0.09
    puter
    0.09
    Activations Density 0.021%

    No Known Activations