© 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. 1974
    Prev
    Next
    INDEX
    Explanations

    ac.uk, .it, Region, .ac, Hospital

    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
    åŀĽ
    -0.10
    çģĮ
    -0.09
     fur
    -0.09
    è¿Ħ
    -0.09
    秧
    -0.08
    åģ¶
    -0.08
    нов
    -0.08
     Nurs
    -0.08
    cole
    -0.08
    æĭ¶
    -0.08
    POSITIVE LOGITS
     DISCLAIMER
    0.10
     xuân
    0.09
    arti
    0.09
    èĵij
    0.09
    rub
    0.09
    æį¢äºĨ
    0.08
    itung
    0.08
    alık
    0.08
     Lug
    0.08
    ä¸Ĭå¹´
    0.08
    Activations Density 0.001%

    No Known Activations