© 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. 54817
    Prev
    Next
    INDEX
    Explanations

    slightly indicating degree

    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
    ç¿»
    -0.11
    åįģ足
    -0.09
     flips
    -0.09
    éļĶ
    -0.09
     пеÑĢем
    -0.09
    æĹłéĻIJ
    -0.09
    çĸı
    -0.08
    åķĨåѦéĻ¢
    -0.08
    PTY
    -0.08
     flip
    -0.08
    POSITIVE LOGITS
    çķ¥æľī
    0.13
    çķ¥å¾®
    0.10
    ä¸ĢçĤ¹çĤ¹
    0.10
     slightly
    0.10
    ä¼łè¯´
    0.09
     slight
    0.09
    _INLINE
    0.09
    å°ijéĩı
    0.09
    çļĦæĶ¯æĮģ
    0.09
    akh
    0.09
    Activations Density 0.041%

    No Known Activations