© 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. 54097
    Prev
    Next
    INDEX
    Explanations

    proceed to do something

    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
    æīĢæıIJä¾Ľ
    -0.09
     Tol
    -0.09
    olio
    -0.09
    zee
    -0.09
    æīĢæıIJä¾ĽçļĦ
    -0.09
    åĹŁ
    -0.09
    æĢķ
    -0.08
     tol
    -0.08
    æĽ¾
    -0.08
    æĪijçŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    rench
    0.10
    upa
    0.09
    -INF
    0.09
    为客æĪ·
    0.09
    ç©¿ä¸Ĭ
    0.09
    Qualified
    0.09
    stüt
    0.08
    对åħ¬åı¸
    0.08
    vak
    0.08
    åIJĪæł¼
    0.08
    Activations Density 0.004%

    No Known Activations