© 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. 39843
    Prev
    Next
    INDEX
    Explanations

    a cover, duplicate, value, canon, correct, id, fighter

    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
    даÑĢ
    -0.10
    ry
    -0.09
    åĮ¡
    -0.09
    portun
    -0.09
    RY
    -0.09
    icum
    -0.08
    ä¹Łå°±æĺ¯
    -0.08
    çļĦä¸ĢåĪĩ
    -0.08
    æijŃ
    -0.08
    inky
    -0.08
    POSITIVE LOGITS
    羣å®ŀçļĦ
    0.12
     valid
    0.11
     contender
    0.10
    羣å®ŀ
    0.10
    æŃ£å¸¸çļĦ
    0.10
     existing
    0.10
    æľīæķĪçļĦ
    0.09
    çİ°æľīçļĦ
    0.09
     available
    0.09
    åIJĪæ³ķ
    0.09
    Activations Density 0.204%

    No Known Activations