© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7329
    Prev
    Next
    INDEX
    Explanations

    python scripts / code

    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
    ä¸įçŁ¥
    -0.08
     chiếu
    -0.08
    affle
    -0.08
    æľº
    -0.08
     craz
    -0.08
    'a
    -0.08
    TickCount
    -0.08
    erald
    -0.08
    ework
    -0.07
    çѵ
    -0.07
    POSITIVE LOGITS
    æĽ´å¤ļçļĦæĺ¯
    0.09
    AMI
    0.09
    ØŁ
    0.09
    ä¸įåıĬ
    0.08
    ä»ĸ说
    0.08
    å¨ģåĬĽ
    0.08
    åıĸåĨ³
    0.08
    contr
    0.08
     קש×Ķ
    0.08
     podcast
    0.07
    Activations Density 0.026%

    No Known Activations