© 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. 27071
    Prev
    Next
    INDEX
    Explanations

    punk, gainsbourg, scicos, frama-c, traefik, .com, .ie

    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
    æĿ¾å¼Ľ
    -0.09
     Ging
    -0.09
    ANGO
    -0.09
    виÑĤ
    -0.09
    çıį
    -0.08
    å°İ
    -0.08
     vain
    -0.08
    jam
    -0.08
    enerate
    -0.08
    ients
    -0.08
    POSITIVE LOGITS
    为äºĨæĽ´å¥½
    0.09
    寰
    0.09
    ä¸Ģéĥ¨
    0.08
    åİŁèijĹ
    0.08
    /groups
    0.08
    éĻ¢å£«
    0.08
    rong
    0.08
    ä¸Ģæµģ
    0.08
     @@
    0.07
    .ev
    0.07
    Activations Density 0.001%

    No Known Activations