© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    被åĬ¨
    -0.10
    èµĽåIJİ
    -0.10
    _lens
    -0.09
    æģ£
    -0.09
    è¶ħé¢Ŀ
    -0.09
    æĭ¦
    -0.09
    åIJ¯è¿ª
    -0.08
    eron
    -0.08
    纳æĸ¯
    -0.08
    ожно
    -0.08
    POSITIVE LOGITS
     formal
    0.11
    è¾Ľè¾£
    0.11
     commitment
    0.10
    éĤ£ä¹Īå¤ļ
    0.09
    æķıæĦŁ
    0.09
    åĨĴéĻ©
    0.09
    ä¹Łä¸įæĥ³
    0.09
    oria
    0.09
    çļĦä¼łç»Ł
    0.09
    嵩
    0.09
    Activations Density 0.123%

    No Known Activations