© 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. 17507
    Prev
    Next
    INDEX
    Explanations

    way

    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
    è§ľ
    -0.09
    æľĢä½³
    -0.09
    odal
    -0.09
    Ùģار
    -0.09
    inus
    -0.09
    çļĦéĤ£ç§į
    -0.09
    oyer
    -0.09
    ä¸įå·²
    -0.08
    ä¹ĭäºĭ
    -0.08
    outes
    -0.08
    POSITIVE LOGITS
    è¶Ł
    0.12
    çľ·
    0.09
    acre
    0.09
    æįŀ
    0.08
    å¦ĤæĦı
    0.08
     unofficial
    0.08
    è¾ľè´Ł
    0.08
    åİŁå§ĭ
    0.08
    æĪIJç«ĭ以æĿ¥
    0.08
    ÑĥÑĩа
    0.08
    Activations Density 0.020%

    No Known Activations