© 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. 36291
    Prev
    Next
    INDEX
    Explanations

    solo, lone, singleton

    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
    è·Ĺ
    -0.12
    å½¼
    -0.11
    åIJı
    -0.09
    /ajax
    -0.09
    ĪæĿĥ
    -0.09
    ENC
    -0.09
    åķľ
    -0.08
    ê²IJ
    -0.08
    éĻ
    -0.08
    egin
    -0.08
    POSITIVE LOGITS
    å¾ĢåIJİ
    0.08
    å¥¹åľ¨
    0.08
    ément
    0.08
    [--
    0.08
    åı£åij³
    0.07
    (mut
    0.07
    cker
    0.07
     Buen
    0.07
    uv
    0.07
    bright
    0.07
    Activations Density 0.005%

    No Known Activations