© 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. 23753
    Prev
    Next
    INDEX
    Explanations

    establishment and establishment of

    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
    igu
    -0.10
    ä¾Ī
    -0.10
    cip
    -0.10
    æ£ļ
    -0.09
    .struts
    -0.09
    opy
    -0.09
    å¯Ĥå¯ŀ
    -0.09
    åŃļ
    -0.09
    åįģ足
    -0.09
    etch
    -0.09
    POSITIVE LOGITS
    OrUpdate
    0.12
    ively
    0.11
    æĸ°çļĦ
    0.10
    ¡
    0.10
    åĴĮåıijå±ķ
    0.10
    äºĨä¸Ģ个
    0.09
    ellt
    0.09
    åĴĮå®ĮåĸĦ
    0.09
    ä¸İåıijå±ķ
    0.08
    ä¹ĭåĪĿ
    0.08
    Activations Density 0.034%

    No Known Activations