© 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. 23157
    Prev
    Next
    INDEX
    Explanations

    exercise and related measurements

    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
    æĭ¿æĿ¥
    -0.10
    好äºĨ
    -0.09
    elter
    -0.08
    æĸ¹æ³ķ
    -0.08
    atter
    -0.08
    éĽĨ
    -0.08
    VEST
    -0.08
    afc
    -0.08
    çĪª
    -0.08
    ars
    -0.08
    POSITIVE LOGITS
    æĵĢ
    0.10
    åķ¶
    0.10
    æıIJè´¨
    0.10
    书ä¸Ń
    0.09
    gree
    0.09
    ç»ı纪
    0.09
    è¿ĩåħ³
    0.09
    å¾®ç¬ij
    0.09
    .Acc
    0.09
    PIO
    0.09
    Activations Density 0.090%

    No Known Activations