© 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. 11796
    Prev
    Next
    INDEX
    Explanations

    not a complete list

    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
    gross
    -0.09
    è°Ī
    -0.09
    æĮ¯åħ´
    -0.09
     gross
    -0.08
     Gross
    -0.08
    è¨Ģ
    -0.08
    æ·¡æ°´
    -0.08
    raw
    -0.08
     lean
    -0.08
    .dest
    -0.08
    POSITIVE LOGITS
    ä¸Ģå®ļèĥ½
    0.13
    æľĢæĸ°
    0.10
     necessarily
    0.10
    haust
    0.10
    ستاÙĨ
    0.09
     exhaustive
    0.09
    æľīå¤ļä¹Ī
    0.09
    æĹĮ
    0.09
    åĿıäºĭ
    0.09
    latest
    0.09
    Activations Density 0.044%

    No Known Activations