© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7964
    Prev
    Next
    INDEX
    Explanations

    McCain, McCoy, Flake, Marker

    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
    vard
    -0.09
    eltas
    -0.09
    /sdk
    -0.09
    gg
    -0.09
    åŃ¦å®¶
    -0.08
    ç°¸
    -0.08
    kop
    -0.08
    ÑįÑĤомÑĥ
    -0.08
    éĿ¢ä¸Ĭ
    -0.08
    åĽ½æĥħ
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.11
    æĵ¿
    0.10
    OrUpdate
    0.10
    ä¸įåIJĮç¨ĭ度
    0.09
    /gtest
    0.09
    quire
    0.09
    èĢģåħµ
    0.09
    ðŁı¼
    0.09
    igh
    0.09
    avis
    0.09
    Activations Density 0.001%

    No Known Activations