© 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. 27923
    Prev
    Next
    INDEX
    Explanations

    be relied upon

    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
    æĸŃ
    -0.08
    8
    -0.08
    ä¾Ŀæīĺ
    -0.08
    ä¸įåı¯èĥ½
    -0.08
    两边
    -0.08
    1
    -0.08
    6
    -0.08
    9
    -0.07
    2
    -0.07
     packs
    -0.07
    POSITIVE LOGITS
    ä½ıåĿĢ
    0.10
    ç«Ļéķ¿
    0.09
    itus
    0.09
    æIJ¬åĪ°
    0.09
     Pedro
    0.09
    滹
    0.09
    æĶ¹ç¼ĸ
    0.09
    æīĵåĵį
    0.09
    æ¢ĥ
    0.09
    alse
    0.09
    Activations Density 0.028%

    No Known Activations