© 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. 19292
    Prev
    Next
    INDEX
    Explanations

    live in

    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
    å½Ŀ
    -0.10
    OfWork
    -0.09
    WithContext
    -0.09
    اÙĨÙĬ
    -0.08
    stry
    -0.08
     overall
    -0.08
     Victor
    -0.08
    olean
    -0.08
    omaly
    -0.08
    /channel
    -0.08
    POSITIVE LOGITS
     sucker
    0.09
    /exec
    0.09
    akes
    0.08
    æģ¯
    0.08
    èı©èIJ¨
    0.08
    pir
    0.08
    utting
    0.08
    PRS
    0.08
    ied
    0.08
    çľ·
    0.08
    Activations Density 0.045%

    No Known Activations