© 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. 48023
    Prev
    Next
    INDEX
    Explanations

    committed to

    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
    ôi
    -0.09
     fas
    -0.08
    prep
    -0.08
    رب
    -0.08
    æĢ¨
    -0.08
    /IP
    -0.08
    ton
    -0.08
    羣æŃ£
    -0.08
    isser
    -0.08
    好人
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įæĥ³
    0.11
    éĢıè¿ĩ
    0.10
    ucked
    0.10
    æľīèĩªå·±çļĦ
    0.10
    为æĤ¨
    0.09
     gamm
    0.09
    çĤľ
    0.09
    çĽ¯çĿĢ
    0.09
    æĬĬä½ł
    0.09
    è¿Ļæł·åģļ
    0.09
    Activations Density 0.017%

    No Known Activations