© 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. 49121
    Prev
    Next
    INDEX
    Explanations

    companies such as LLC, Ltd, Pty, d.o.o

    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
     stroke
    -0.09
     strokes
    -0.09
     impression
    -0.09
    Engine
    -0.08
    çļĦä¼łç»Ł
    -0.08
    ronic
    -0.08
    å°±æĬĬ
    -0.08
    éķĤ
    -0.08
    åIJĪè§Ħ
    -0.08
    วà¸Ķ
    -0.08
    POSITIVE LOGITS
    æľīéĻIJåħ¬åı¸
    0.13
    åħ¬åı¸çļĦ
    0.10
    åħ¬åı¸
    0.10
    è¯ī
    0.10
    æī¿æİ¥
    0.10
     gamb
    0.09
    æľīéĻIJ责任
    0.09
    建åįİ
    0.09
    usk
    0.09
    ä¼łåĩº
    0.09
    Activations Density 0.111%

    No Known Activations