© 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. 12058
    Prev
    Next
    INDEX
    Explanations

    elusive

    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
    expo
    -0.10
    èµİ
    -0.09
    èĿĻ
    -0.09
    èĬ
    -0.09
    åĭĩæ°Ķ
    -0.09
    /native
    -0.09
     oluÅŁan
    -0.09
    ä¹Łæľī
    -0.09
    转åĮĸ
    -0.09
    bat
    -0.09
    POSITIVE LOGITS
     elusive
    0.19
     grasp
    0.09
    潤
    0.09
    éļ¾ä»¥
    0.09
    æ¶Ī失äºĨ
    0.09
    ispers
    0.09
    æºľ
    0.09
    设æĸ½å»ºè®¾
    0.09
    æĭĴ
    0.08
     escaping
    0.08
    Activations Density 0.071%

    No Known Activations