© 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. 38403
    Prev
    Next
    INDEX
    Explanations

    currency amounts and numbers

    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
    建设çĶ¨åľ°
    -0.09
    å²ģæŶ
    -0.08
    åĴ¦
    -0.08
     Ñģвое
    -0.08
    åĩĢåľŁ
    -0.08
    iami
    -0.08
    BuilderFactory
    -0.08
    ëłĮ
    -0.08
    owering
    -0.07
    ä¸įèĤ¯
    -0.07
    POSITIVE LOGITS
    约åIJĪ
    0.14
    å¥Ķæ³¢
    0.10
    translator
    0.10
    è¯ij
    0.09
    ç¿»è¯ij
    0.09
    avian
    0.09
    ä¸ĢåĢĭ人
    0.09
    ä¸Ģ个人
    0.09
    strings
    0.09
    ensch
    0.08
    Activations Density 0.021%

    No Known Activations