© 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. 10724
    Prev
    Next
    INDEX
    Explanations

    Representative or Senator

    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
     atl
    -0.09
    å¿ł
    -0.09
     ATL
    -0.09
    æĽ³
    -0.09
    gps
    -0.09
    olson
    -0.08
    _gps
    -0.08
     enumerated
    -0.08
    GPS
    -0.08
    æĦŁè§ī
    -0.08
    POSITIVE LOGITS
    è°±åĨĻ
    0.10
    nie
    0.09
    åľ¨å½ĵåľ°
    0.09
    å¢Ł
    0.09
     Prospect
    0.08
    elligent
    0.08
    /LICENSE
    0.08
    åľ¨è¿Ļ个
    0.08
    æıIJ示
    0.08
    ç¥ī
    0.08
    Activations Density 0.030%

    No Known Activations