© 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. 37860
    Prev
    Next
    INDEX
    Explanations

    second followed by a noun

    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
    ä¸įæĸŃæıIJé«ĺ
    -0.11
    QObject
    -0.10
    .Redirect
    -0.09
    éĶĻäºĨ
    -0.09
    æݳ
    -0.09
     UNITY
    -0.09
    æīĵæī®
    -0.09
    è¿Ļ座
    -0.09
    arte
    -0.09
    çİĭåŃIJ
    -0.08
    POSITIVE LOGITS
    äººåľ¨
    0.09
    yre
    0.09
    влекаÑĤелÑĮ
    0.08
    ç
    0.08
     Wein
    0.08
    oul
    0.08
    vious
    0.08
    _bs
    0.08
    ç±½
    0.08
    вол
    0.08
    Activations Density 0.021%

    No Known Activations