© 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. 35387
    Prev
    Next
    INDEX
    Explanations

    evil and villains

    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
    IAL
    -0.09
    une
    -0.09
    å°ı康
    -0.08
    RefPtr
    -0.08
    .listen
    -0.08
    纵åIJij
    -0.08
    eus
    -0.08
    èĦĨ
    -0.08
    gil
    -0.08
    çıįæĥľ
    -0.08
    POSITIVE LOGITS
    æģ¨ä¸įå¾Ĺ
    0.12
     vil
    0.11
    éĤªæģ¶
    0.11
    æķĮ人
    0.11
    åĿŀ
    0.11
    vil
    0.11
    对ç«ĭ
    0.10
    æī¼
    0.10
    éĥ½è¢«
    0.10
    è¯ĭ
    0.10
    Activations Density 0.121%

    No Known Activations