© 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. 26475
    Prev
    Next
    INDEX
    Explanations

    CV or biographical information

    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
    éĩįçİ°
    -0.10
    Ñįм
    -0.09
    主æĦı
    -0.08
     Severity
    -0.08
    æĦı
    -0.08
    ä¼´
    -0.08
    ä½ĵéªĮ
    -0.08
    irect
    -0.08
    ç»Ŀ
    -0.08
    秩åºı
    -0.08
    POSITIVE LOGITS
    ç®ĢåİĨ
    0.23
    å±¥
    0.22
     profile
    0.17
    .profile
    0.16
    /profile
    0.15
    (profile
    0.14
    -profile
    0.14
    _profile
    0.14
    PROFILE
    0.14
    profile
    0.14
    Activations Density 0.160%

    No Known Activations