© 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. 22618
    Prev
    Next
    INDEX
    Explanations

    exoplanets, interact, discovery, search

    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
    icot
    -0.09
    elic
    -0.09
    łģ
    -0.09
    conds
    -0.09
     tav
    -0.09
    URN
    -0.09
    çľŁç©º
    -0.09
    ç°ª
    -0.09
    许åı¯
    -0.09
    atem
    -0.08
    POSITIVE LOGITS
    åŃ
    0.10
    æİĢ
    0.09
    .dispose
    0.09
    нÑĮ
    0.09
    éĶī
    0.09
    åĪ¶åº¦æĶ¹éĿ©
    0.08
    è¿Īåĩº
    0.08
    ä¾į
    0.08
    çijŁ
    0.08
    æµ·å¤ĸ
    0.08
    Activations Density 0.037%

    No Known Activations