© 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. 56794
    Prev
    Next
    INDEX
    Explanations

    out of the box

    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
    sted
    -0.11
     ë¬¼ë¡ł
    -0.11
    ç¿ħèĨĢ
    -0.10
    æĥķ
    -0.09
    ucker
    -0.09
    ê¹IJ
    -0.09
    stead
    -0.09
    åĽŀé¦ĸ
    -0.09
     getArguments
    -0.09
    .struct
    -0.09
    POSITIVE LOGITS
    6
    0.09
    abouts
    0.09
    hlen
    0.09
    讨
    0.09
    éĴ¦
    0.09
    éĤ£ä¸ªäºº
    0.09
    andel
    0.08
    4
    0.08
    顺
    0.08
    ness
    0.08
    Activations Density 0.022%

    No Known Activations