© 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. 38852
    Prev
    Next
    INDEX
    Explanations

    list items separated by commas or and

    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
    achten
    -0.09
    rze
    -0.08
    纵è§Ĥ
    -0.08
    nell
    -0.08
    fäh
    -0.08
    inherits
    -0.08
    _VEC
    -0.08
    ARB
    -0.08
    åľ¨
    -0.08
     Thousand
    -0.08
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯è¯´
    0.11
    /or
    0.10
    è¿Ļå°±
    0.10
    çĸ³
    0.09
     tức
    0.09
    èĢĮåıĪ
    0.09
     either
    0.09
    æĸ°å¨ĺ
    0.09
    ä¹Łå°±æĺ¯
    0.08
    è¿Ļå°±æĺ¯
    0.08
    Activations Density 1.133%

    No Known Activations