© 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. 10413
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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
    级åĪ«çļĦ
    -0.09
    级åĪ«
    -0.09
    æŁ´æ²¹
    -0.09
    lund
    -0.08
    ä¸įä¸ĭ
    -0.08
    -worthy
    -0.08
    æĺ¯éĿŀ
    -0.08
    ocha
    -0.08
     clearance
    -0.08
    tic
    -0.07
    POSITIVE LOGITS
    æķ°åŃĹ
    0.12
    çĪ¬ä¸Ĭ
    0.11
     numbers
    0.11
    igits
    0.10
    ìĪ
    0.10
    -ft
    0.10
    à¹ĩà¸Ķ
    0.10
    å¥
    0.10
    numbers
    0.10
    ä»ħ代表
    0.09
    Activations Density 0.227%

    No Known Activations