© 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. 33618
    Prev
    Next
    INDEX
    Explanations

    from across

    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
    дав
    -0.10
    äºĮèĢħ
    -0.09
    èĥ½åģļåĪ°
    -0.08
    ä¸ĭ乡
    -0.08
    .ov
    -0.08
    两èĢħ
    -0.08
    éĻĪåĪĹ
    -0.08
    ä¼łå¯¼
    -0.08
    åĵº
    -0.08
    泫
    -0.08
    POSITIVE LOGITS
    æĿ¥èĩª
    0.18
    ä¾Ĩèĩª
    0.16
    åħ¨åĽ½åIJĦåľ°
    0.16
    ä¸ĸçķĮåIJĦåľ°
    0.14
    æĿ¥èĩªäºİ
    0.13
     across
    0.13
    ä¸įåIJĮ
    0.12
     khắp
    0.12
    éģįå¸ĥ
    0.12
    åĪ°æĿ¥
    0.11
    Activations Density 0.091%

    No Known Activations