© 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. 55218
    Prev
    Next
    INDEX
    Explanations

    where is the

    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
    æľīäºĨ
    -0.09
     bosses
    -0.08
    æĨ¬
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    lox
    -0.08
    oug
    -0.08
     k
    -0.08
    سÙĬر
    -0.07
    TXT
    -0.07
    è¿¥
    -0.07
    POSITIVE LOGITS
    ä¸İåıijå±ķ
    0.11
    æ·¹
    0.10
    éĤ£ä¸ªäºº
    0.10
    urus
    0.10
    unami
    0.10
     ÑģобÑģÑĤвенно
    0.09
    å»ĭ
    0.09
    åijĢ
    0.09
     ÑģÑĢеди
    0.09
    æĹłå£°
    0.09
    Activations Density 0.034%

    No Known Activations