© 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. 37989
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    ãģĹãģ¾ãģĨ
    -0.18
    ãģĹãģ¾
    -0.14
    ãģĹãģ¾ãģĦ
    -0.12
    iday
    -0.11
    -0.10
    goo
    -0.10
    otti
    -0.09
    imar
    -0.09
     mÃŃ
    -0.09
    åīįæīĢ
    -0.08
    POSITIVE LOGITS
    ions
    0.12
    zelf
    0.10
    IONS
    0.10
    ataire
    0.09
     ìķĦëĭĪëĿ¼
    0.09
    ataires
    0.09
     же
    0.09
    ÑĪек
    0.09
    ãģ£ãģĵ
    0.08
     Ñģобой
    0.08
    Activations Density 0.128%

    No Known Activations