© 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. 30071
    Prev
    Next
    INDEX
    Explanations

    wonder how

    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
    æĽ·
    -0.10
    å±ł
    -0.09
    æĽ¼
    -0.09
    交éĻħ
    -0.09
    纳æĸ¯
    -0.08
    åİŁåĪĻä¸Ĭ
    -0.08
    ам
    -0.08
    ä¹ĭæīĢ以
    -0.08
    èĬ©
    -0.08
    æľ¬æĿ¥å°±
    -0.08
    POSITIVE LOGITS
     dozen
    0.10
    èĬĹ
    0.09
    atalog
    0.09
    виз
    0.09
    æIJŃ
    0.08
    ôle
    0.08
    ä»ĸä»¬åľ¨
    0.08
    éĽĴ
    0.08
    æĻ°
    0.08
    olie
    0.08
    Activations Density 0.012%

    No Known Activations