© 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. 51011
    Prev
    Next
    INDEX
    Explanations

    University names

    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
    odb
    -0.10
    ç½ijå°ıç¼ĸ
    -0.10
    eenth
    -0.09
    íĥĦ
    -0.08
    èĴ¯
    -0.08
    ì²Ļ
    -0.08
    æĪ¿ä¸ľ
    -0.08
    éļıæīĭ
    -0.08
    åķĨæĬ¥
    -0.08
     Bon
    -0.08
    POSITIVE LOGITS
    稷
    0.10
    izable
    0.09
     hairy
    0.09
    kal
    0.09
    igor
    0.08
    æŁı
    0.08
    grounds
    0.08
     بغ
    0.08
    หม
    0.08
    PX
    0.08
    Activations Density 0.028%

    No Known Activations