© 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. 56942
    Prev
    Next
    INDEX
    Explanations

    why questions

    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
    ichel
    -0.10
    åŁł
    -0.10
     Ấ
    -0.09
    ÙĦس
    -0.09
     Ply
    -0.09
    èĶ¼
    -0.08
    еÑĩа
    -0.08
    è§ĨåIJ¬
    -0.08
    abis
    -0.08
    ä¿ĺ
    -0.08
    POSITIVE LOGITS
    ever
    0.10
    éĤ£ä¹Īå¤ļ
    0.10
    让åŃ©åŃIJ
    0.09
    æĪIJçĨŁçļĦ
    0.09
    ÑĤÑĢ
    0.09
    åģıåģı
    0.09
    æ®ļ
    0.09
     вообÑīе
    0.09
    tre
    0.09
    cen
    0.09
    Activations Density 0.019%

    No Known Activations