© 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. 17019
    Prev
    Next
    INDEX
    Explanations

    5-year survival

    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
    èĢĺ
    -0.10
    Ļ¶
    -0.10
    é£İ鼨
    -0.10
    anders
    -0.09
    å¢ĥå¤ĸ
    -0.09
    é«ĺä»·
    -0.08
    æı£
    -0.08
    éĤĽ
    -0.08
    룬
    -0.08
    常
    -0.08
    POSITIVE LOGITS
    ç¿ģ
    0.09
    æ¼ı
    0.09
     imper
    0.09
    OPS
    0.09
    fmt
    0.09
    æķķ
    0.09
    opro
    0.09
    åŃĹ
    0.09
    å¤ļå¹´çļĦ
    0.08
    ikki
    0.08
    Activations Density 0.218%

    No Known Activations