© 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. 27028
    Prev
    Next
    INDEX
    Explanations

    invention relates to method

    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
     AUTHORS
    -0.12
    举
    -0.10
    åIJĥåĪ°
    -0.10
    éĻ¶
    -0.10
    .Formatter
    -0.09
    æĭ¼
    -0.09
    ItemType
    -0.09
    гад
    -0.09
     PROCUREMENT
    -0.09
    agara
    -0.09
    POSITIVE LOGITS
    ä¹IJåĻ¨
    0.13
    æ¼Ķå¥ı
    0.12
     Nashville
    0.10
     instrument
    0.09
    åı³æīĭ
    0.09
    æĸ«
    0.08
    ç¥ī
    0.08
    æĬĢå¸Ī
    0.08
    ç»ĥä¹ł
    0.08
    æĿĸ
    0.08
    Activations Density 0.071%

    No Known Activations