© 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. 31374
    Prev
    Next
    INDEX
    Explanations

    independently or independent

    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
    è¡Ķ
    -0.10
    ä¸įåĩĨ
    -0.09
    ç¬ķ
    -0.09
    phe
    -0.09
    CBC
    -0.09
    dio
    -0.09
    æµģåĬ¨æĢ§
    -0.09
     skÅĤ
    -0.09
     Unblock
    -0.09
     ÐŁÐµÑĤÑĢ
    -0.09
    POSITIVE LOGITS
    iable
    0.11
    iates
    0.10
    ä¹İ
    0.09
    iating
    0.09
    æĺ¯ä¸Ģéĥ¨
    0.09
    ively
    0.09
    缩
    0.08
     Baxter
    0.08
    2
    0.08
    4
    0.08
    Activations Density 0.031%

    No Known Activations