© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36421
    Prev
    Next
    INDEX
    Explanations

    unified approach

    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
     unborn
    -0.10
     Beit
    -0.09
    人éĢī
    -0.09
    è¾¼ãģ¿
    -0.09
    _nsec
    -0.09
     usual
    -0.09
    ECH
    -0.09
    side
    -0.08
    ials
    -0.08
    gression
    -0.08
    POSITIVE LOGITS
    itarian
    0.11
    ä¼ļéķ¿
    0.10
    itaire
    0.10
    ursal
    0.09
    iswa
    0.09
    .lin
    0.09
    izable
    0.08
    åī¯å±Ģéķ¿
    0.08
    à¸Ńาร
    0.08
    جاÙĨ
    0.08
    Activations Density 0.032%

    No Known Activations