© 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. 2986
    Prev
    Next
    INDEX
    Explanations

    car models and brands

    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
    éĬ®
    -0.09
    åijĬ
    -0.08
    ä¹Łå°±æĺ¯
    -0.08
    绵
    -0.08
    wort
    -0.08
    ArrayOf
    -0.08
    æĿijæĿijæ°ij
    -0.08
     wander
    -0.08
     Wald
    -0.08
    è´¢æĶ¿éĥ¨
    -0.08
    POSITIVE LOGITS
    idar
    0.11
     Seah
    0.10
    tá
    0.10
    RIES
    0.09
     ÙħجÙĦ
    0.09
    opor
    0.08
     зÑĢ
    0.08
    osas
    0.08
    idth
    0.08
    æ´Ĺ礼
    0.08
    Activations Density 0.007%

    No Known Activations