© 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. 11004
    Prev
    Next
    INDEX
    Explanations

    get method

    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
    OLE
    -0.10
    itect
    -0.09
    åIJĦèĩªçļĦ
    -0.08
    çļĦ社ä¼ļ
    -0.08
    iterate
    -0.08
    .NET
    -0.08
    åIJĮæľŁ
    -0.08
    æİ¥çĿĢ
    -0.08
    onde
    -0.08
    italize
    -0.08
    POSITIVE LOGITS
    tings
    0.17
    TING
    0.16
    ters
    0.16
    ComputedStyle
    0.15
    ween
    0.14
    timeofday
    0.13
     rid
    0.13
    sockopt
    0.12
    ting
    0.12
    aways
    0.12
    Activations Density 0.147%

    No Known Activations