© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35925
    Prev
    Next
    INDEX
    Explanations

    verbs following commas

    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
    3
    -0.10
    å®ŀå®ŀåľ¨åľ¨
    -0.10
    颤
    -0.09
    è¿ĻæĿ¡
    -0.09
    1
    -0.09
    æĪIJ为ä¸ĢåIJį
    -0.09
    çļĦ羣å®ŀæĢ§
    -0.09
    /embed
    -0.09
    9
    -0.09
    8
    -0.09
    POSITIVE LOGITS
    妩
    0.10
    å«¡
    0.09
    à¸Ĭำ
    0.08
    bench
    0.08
    红æĹĹ
    0.08
    èĮħ
    0.08
     plum
    0.08
    áĥij
    0.08
    bor
    0.08
    æĪª
    0.08
    Activations Density 0.046%

    No Known Activations