© 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. 61048
    Prev
    Next
    INDEX
    Explanations

    award or prize name ending

    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
    ä¸įåĩĨ
    -0.09
    amel
    -0.09
    ØŃÙĦ
    -0.09
    çļĦæĥħ
    -0.09
    çļĦç»ıåħ¸
    -0.08
    é¡
    -0.08
    åıijéŁ³
    -0.08
    .removeClass
    -0.08
    iche
    -0.08
    è§Ħ模以ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    å¥ĸ
    0.14
    æĿ¯
    0.13
    Award
    0.11
     Award
    0.11
    æıIJåIJį
    0.11
    æľĢä½³
    0.11
    çįİ
    0.10
     award
    0.10
     Awards
    0.10
     awards
    0.10
    Activations Density 0.035%

    No Known Activations