© 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. 48137
    Prev
    Next
    INDEX
    Explanations

    of whom

    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
    achi
    -0.09
    SEMB
    -0.09
    cence
    -0.09
    æĹ»
    -0.08
    instein
    -0.08
    .APPLICATION
    -0.08
    åİ¢
    -0.08
     Votes
    -0.08
    stime
    -0.08
    人å±ħçݯå¢ĥ
    -0.08
    POSITIVE LOGITS
     whose
    0.11
     коÑĤоÑĢой
    0.10
     коÑĤоÑĢÑĭÑħ
    0.10
    大éĥ¨åĪĨ
    0.10
     which
    0.10
    ä¸Ģçľ¼
    0.09
    whose
    0.09
     коÑĤоÑĢого
    0.09
    åĿ¡
    0.09
    ä¸Ģ个æĺ¯
    0.08
    Activations Density 0.112%

    No Known Activations