© 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. 38617
    Prev
    Next
    INDEX
    Explanations

    spam, bots, fake degrees, publishing fraud

    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
    æĹ¥æŃ£å¼ı
    -0.10
     extrad
    -0.10
    é¢ĺ主
    -0.09
    çIJĩ
    -0.09
    ä¸įå®ļ
    -0.09
    çĹ
    -0.09
    .cwd
    -0.09
    ableObject
    -0.09
    INI
    -0.08
    羡
    -0.08
    POSITIVE LOGITS
    伪éĢł
    0.11
    éĩįå¤į
    0.10
    å¥Ĺ
    0.09
    æķħæĦı
    0.09
     ghost
    0.08
    ä½İå»ī
    0.08
    çīŁ
    0.08
    idl
    0.08
    ç¡Ŀ
    0.08
    èĻļåģĩ
    0.08
    Activations Density 0.142%

    No Known Activations