© 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. 18513
    Prev
    Next
    INDEX
    Explanations

    one question

    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
    失
    -0.09
    æĭĴ
    -0.08
    èĢ¿
    -0.08
     знаÑĤÑĮ
    -0.08
    æĺ¥
    -0.08
    æ¡ĥèĬ±
    -0.08
     Tale
    -0.08
     Boeh
    -0.08
    ingly
    -0.08
    æ¢ĵ
    -0.08
    POSITIVE LOGITS
    贯穿
    0.10
    쯤
    0.09
    éĥ½èĥ½å¤Ł
    0.09
    缸è§ģ
    0.09
    .cgi
    0.08
    å¾Īéĩįè¦ģçļĦ
    0.08
    貫
    0.08
    _BGR
    0.08
    _DECLARE
    0.08
    .GetProperty
    0.08
    Activations Density 0.135%

    No Known Activations