© 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. 2314
    Prev
    Next
    INDEX
    Explanations

    intellectual property licensing and royalties

    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
    åħ¬ç½ijå®īå¤ĩ
    -0.09
    伺
    -0.09
    flare
    -0.08
    -pill
    -0.08
     preamble
    -0.08
    纯粹
    -0.08
    åIJĮä¼´
    -0.08
    æݬ
    -0.08
    unsch
    -0.08
    é¢łè¦Ĩ
    -0.08
    POSITIVE LOGITS
    çŁ¥è¯Ĩ产æĿĥ
    0.14
    æİĪæĿĥ
    0.14
    çīĪæĿĥ
    0.13
    许åı¯
    0.13
     intellectual
    0.11
     Intellectual
    0.11
    æİĪæ¬Ĭ
    0.10
     royalties
    0.10
    ä¸ĵåĪ©
    0.10
    _busy
    0.10
    Activations Density 0.205%

    No Known Activations