© 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. 62144
    Prev
    Next
    INDEX
    Explanations

    quantifiers or types

    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
    ogie
    -0.09
    çģ«èĬ±
    -0.09
     _|
    -0.09
    æ¿Ģèµ·
    -0.09
    OCUS
    -0.09
    ä¾Ķ
    -0.09
    erved
    -0.08
    é¡·
    -0.08
    GINE
    -0.08
    åŃ°
    -0.08
    POSITIVE LOGITS
    åľ¨åĨħçļĦ
    0.18
    ä½Ĩä¸įéĻIJäºİ
    0.13
    ä½Ĩä¸įéĻIJ
    0.13
    åľ¨éĩĮéĿ¢
    0.12
    è¿ĺåĮħæĭ¬
    0.10
    ä¸įå°ıçļĦ
    0.10
    çļĦæīĢæľī
    0.10
    ä¸Ģ缴éĥ½
    0.09
    äºĨ好åĩł
    0.09
    æīĢæľī人
    0.09
    Activations Density 0.327%

    No Known Activations