© 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. 27925
    Prev
    Next
    INDEX
    Explanations

    completion of activities

    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
    (td
    -0.09
     мн
    -0.09
    holder
    -0.08
    anded
    -0.08
    æŃī
    -0.08
    aming
    -0.08
    /cms
    -0.08
    ogenic
    -0.08
    è¸Ķ
    -0.08
    entions
    -0.08
    POSITIVE LOGITS
    äºĨèĩªå·±çļĦ
    0.11
    lich
    0.10
    äºĨä»ĸçļĦ
    0.10
    æĤłæĤł
    0.09
    åIJĦèĩªçļĦ
    0.09
     ÑĢабоÑĤÑĭ
    0.08
    æĺ¥ç§ĭ
    0.08
    wards
    0.08
    ruits
    0.08
    rpc
    0.08
    Activations Density 0.015%

    No Known Activations