© 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. 21625
    Prev
    Next
    INDEX
    Explanations

    start off by

    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
    æ¤Ł
    -0.10
    .fm
    -0.09
    éģ©åIJĪ
    -0.09
    å¦Ĥæľīä¾µæĿĥ
    -0.09
    ä¹Łå¸ĮæľĽ
    -0.09
    çŀ»
    -0.08
    eltas
    -0.08
    æĶ¶éĽĨ
    -0.08
    çºł
    -0.08
    ä¸Ģèµ·åİ»
    -0.08
    POSITIVE LOGITS
    åģļ强
    0.11
    è¿ĻæĿ¡
    0.11
    loi
    0.09
    趾
    0.09
    æľĿ
    0.09
    pers
    0.08
    ramer
    0.08
     Dorm
    0.08
    ä¸įéĶĻ
    0.08
    åī¥
    0.08
    Activations Density 0.024%

    No Known Activations