© 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. 47780
    Prev
    Next
    INDEX
    Explanations

    long before or far from

    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
    ä¸į说
    -0.12
    梧
    -0.11
    ä¸įæĪIJ
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.10
     Eb
    -0.10
    æĹłæ¯Ķ
    -0.10
    æ·ĺ
    -0.10
    çıij
    -0.09
    éĥ¨åĪĨåĨħ容
    -0.09
    弩
    -0.09
    POSITIVE LOGITS
     lắm
    0.10
     enough
    0.10
     anymore
    0.10
    Enough
    0.10
    nor
    0.09
    ousing
    0.09
    èĢĮæĺ¯
    0.09
     ÑģовÑģем
    0.09
     nor
    0.09
     Bee
    0.09
    Activations Density 0.014%

    No Known Activations