© 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. 1777
    Prev
    Next
    INDEX
    Explanations

    get something working

    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
    毫ä¸į
    -0.10
    èĭį
    -0.10
    AbsolutePath
    -0.09
    çĪ¬ä¸Ĭ
    -0.09
    èµ°åIJij
    -0.09
    _REPLACE
    -0.09
     Cutter
    -0.08
    为ä»Ģä¹Īè¦ģ
    -0.08
    éļĪ
    -0.08
    è°ĭ
    -0.08
    POSITIVE LOGITS
    éĻĨç»Ń
    0.09
    åģľçķĻåľ¨
    0.09
     started
    0.08
    ä¸įèĪį
    0.08
    omi
    0.08
     setVisible
    0.08
    èµ·çĤ¹
    0.08
    ä¸įåģľ
    0.08
    绾
    0.08
    cluded
    0.08
    Activations Density 0.054%

    No Known Activations