© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29617
    Prev
    Next
    INDEX
    Explanations

    (C)

    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
    Negative Logits
    ç¨Ķ
    -0.09
    åıį对
    -0.08
    ä¸įéĻIJ
    -0.08
    2
    -0.08
    9
    -0.08
    jen
    -0.08
    sic
    -0.08
    橹
    -0.08
    éĺ¿æł¹
    -0.08
    _FT
    -0.08
    POSITIVE LOGITS
    bung
    0.09
    oodle
    0.09
    _primitive
    0.09
    .$.
    0.09
    ç«ĭéĿ¢
    0.08
    èĬ½
    0.08
    egrity
    0.08
    æĥĬ
    0.08
    æģ¨
    0.08
    rama
    0.08
    Activations Density 0.529%

    No Known Activations