© 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. 18130
    Prev
    Next
    INDEX
    Explanations

    menu, title, screen, credits

    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
    误ä¼ļ
    -0.10
    CHIP
    -0.10
    chip
    -0.10
    è´§æºIJ
    -0.10
    ç»Ħç»ĩé¢Ĩ导
    -0.09
     Ñĥдален
    -0.09
    _DSP
    -0.09
    é¦Ī
    -0.09
    å¢Ļä¸Ĭ
    -0.09
    å¾Ĺ天
    -0.09
    POSITIVE LOGITS
    çĶ»éĿ¢
    0.10
    .gdx
    0.09
     gar
    0.08
    æł¸å¿ĥåĮº
    0.08
    éĹª
    0.08
    è·³
    0.08
     Budd
    0.08
    stitial
    0.08
    çĨĶ
    0.08
    çħ®
    0.08
    Activations Density 0.092%

    No Known Activations