© 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. 54548
    Prev
    Next
    INDEX
    Explanations

    .com/.org URLs and website names

    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
    ä¼ļè§īå¾Ĺ
    -0.09
     Homepage
    -0.09
    æĮ£
    -0.09
    çĵľ
    -0.08
     vert
    -0.08
    丸
    -0.08
     ÑģÑĤоим
    -0.08
    ptype
    -0.08
    èļĢ
    -0.08
     оÑģÑĥÑīеÑģÑĤвлÑı
    -0.08
    POSITIVE LOGITS
    ä¸Ĭ线
    0.10
    çĮ·
    0.10
    åĩĨ
    0.10
    骤
    0.09
    çŁ¿ä¸ļ
    0.09
    flix
    0.09
    女çİĭ
    0.09
    åĵģ
    0.09
    å¸Ĥéķ¿
    0.09
    arya
    0.09
    Activations Density 0.034%

    No Known Activations