© 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. 49301
    Prev
    Next
    INDEX
    Explanations

    lists and enumerations

    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
    иде
    -0.10
    訾
    -0.09
    èķĬ
    -0.09
    ë²Ļ
    -0.09
    ety
    -0.09
    å¼ĭ
    -0.09
    è¾ľè´Ł
    -0.09
    为æѤ
    -0.08
     Naked
    -0.08
    说ä»Ģä¹Ī
    -0.08
    POSITIVE LOGITS
    å¼Ģå±ķäºĨ
    0.10
     Hoy
    0.09
    å®ĮæĪIJäºĨ
    0.09
    å°Ĩèĩªå·±çļĦ
    0.08
    è¿Ľåħ¥äºĨ
    0.08
    æĿĪ
    0.08
    ä¿ĿæĮģçĿĢ
    0.08
    å½¢æĪIJäºĨ
    0.08
    cluding
    0.08
    pot
    0.08
    Activations Density 0.168%

    No Known Activations