© 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. 63039
    Prev
    Next
    INDEX
    Explanations

    Emanuel, Schwimmer, Rita, Clooney

    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
    elve
    -0.08
    gp
    -0.08
    elor
    -0.08
    bole
    -0.08
     SAME
    -0.08
    atable
    -0.08
    oles
    -0.08
    ç¨ĭ
    -0.08
    uan
    -0.08
    asher
    -0.08
    POSITIVE LOGITS
    çļĦåIJĪä½ľ
    0.10
    è¿ŀè¿ŀ
    0.10
    æݬ
    0.10
    çľ¼çľĭ
    0.09
    æĪijçľĭ
    0.09
    ç±³ç²ī
    0.09
    æ¯ĶæĭŁ
    0.09
    çļĦåİĭåĬĽ
    0.09
    çĮĹ
    0.09
     пÑĢоÑģ
    0.09
    Activations Density 0.001%

    No Known Activations