© 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. 63552
    Prev
    Next
    INDEX
    Explanations

    opening or dedication events

    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
    è¡ĮåĬ¨
    -0.11
    ACTION
    -0.10
    æݨéĶĢ
    -0.09
    åĽ°
    -0.09
    æİ¥ä¸ĭæĿ¥
    -0.09
    åħľ
    -0.09
     action
    -0.09
    åĬ¨éĿĻ
    -0.09
     ACTION
    -0.08
    ?action
    -0.08
    POSITIVE LOGITS
    æĬķ产
    0.15
    建æĪIJ
    0.14
    å®Įå·¥
    0.14
    åIJ¯çĶ¨
    0.14
    竣工
    0.13
    éĢļ车
    0.12
    å¼Ģä¸ļ
    0.12
    å¼ĢéĢļ
    0.11
    æĬķåħ¥ä½¿çĶ¨
    0.11
    建æĪIJåIJİ
    0.11
    Activations Density 0.099%

    No Known Activations