© 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. 49302
    Prev
    Next
    INDEX
    Explanations

    deterrent

    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
    累累
    -0.10
    ä¼Ļ
    -0.09
    arov
    -0.09
    iskey
    -0.08
    apult
    -0.08
    驹
    -0.08
    èĥ½ä½¿
    -0.08
    ynet
    -0.08
    åĴ«
    -0.08
     trá»Ŀi
    -0.08
    POSITIVE LOGITS
    rence
    0.13
    å¾Ĺä½ı
    0.10
    ä½ıäºĨ
    0.10
    ingly
    0.10
    èĹľ
    0.10
    妨
    0.09
    idge
    0.09
    iju
    0.09
    ä¸įäºĨ
    0.09
    é¹Ĭ
    0.09
    Activations Density 0.004%

    No Known Activations