© 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. 57505
    Prev
    Next
    INDEX
    Explanations

    time formats

    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
    æĤłæĤł
    -0.10
    å¯Įè´µ
    -0.09
    èĩ¼
    -0.09
    çļĦèĥĮåIJİ
    -0.09
    çıįçıł
    -0.09
    мÑĥ
    -0.09
    ä¸įçĶ¨
    -0.09
    æĺ¥åŃ£
    -0.09
    åİļåİļ
    -0.09
    éºŁ
    -0.08
    POSITIVE LOGITS
    ç¼¢
    0.09
    解æķ£
    0.08
    è¢į
    0.08
    box
    0.08
    æģ¯
    0.08
    éħĿéħ¿
    0.08
    ToObject
    0.08
    å¥ł
    0.08
     ÑģÑĭ
    0.08
    inode
    0.08
    Activations Density 0.042%

    No Known Activations