© 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. 53124
    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
    车åŃIJ
    -0.09
    æĪijçĽ¸ä¿¡
    -0.08
    eking
    -0.08
    eker
    -0.08
    atable
    -0.08
     دÙħØ´
    -0.08
    åĨ·æ°´
    -0.08
    леÑĢ
    -0.08
    arella
    -0.08
    èĥģ
    -0.08
    POSITIVE LOGITS
    两æīĭ
    0.10
    åĬ¨æīĭ
    0.09
    und
    0.09
    igator
    0.09
    unders
    0.09
    ä¸įå°ı
    0.08
    èį
    0.08
    ë²
    0.08
    äºĪ以
    0.08
    æĬ
    0.08
    Activations Density 0.003%

    No Known Activations