© 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. 50653
    Prev
    Next
    INDEX
    Explanations

    academic studies

    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
    åŃIJéĩĮ
    -0.11
    less
    -0.09
    ç¼ĩ
    -0.08
    æĸ¯çī¹
    -0.08
    æĿµ
    -0.08
    happy
    -0.08
    åĦ¿
    -0.08
    .toObject
    -0.08
    ä¸ªå·¥ä½ľ
    -0.08
    omo
    -0.08
    POSITIVE LOGITS
    itia
    0.09
    å¿Ĵ
    0.09
    aylor
    0.09
    eneg
    0.09
    ssi
    0.09
    涯
    0.08
    åIJĽ
    0.08
    æĸ°ç¯ĩç«ł
    0.08
    æł¹åºķ
    0.08
    没åĬŀæ³ķ
    0.08
    Activations Density 0.036%

    No Known Activations