© 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. 31113
    Prev
    Next
    INDEX
    Explanations

    Olympic athletes and 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
    thumbs
    -0.10
    åļ¼
    -0.10
    çĨ¨
    -0.09
    orno
    -0.09
    åı£è¢ĭ
    -0.09
    æĺı
    -0.08
    åĨįéĢł
    -0.08
    ÑģÑĤÑĭ
    -0.08
    _mk
    -0.08
     bitten
    -0.08
    POSITIVE LOGITS
    ä½ĵè´¨
    0.11
    女åŃIJ
    0.10
     Fro
    0.10
    åĩºåĽ½çķĻåѦ
    0.10
    è·ijæŃ¥
    0.10
    æĪIJ绩
    0.09
    é¢Ĩè·ij
    0.09
    éĩijçīĮ
    0.09
    è¿IJåĬ¨åijĺ
    0.09
    è·ijéģĵ
    0.09
    Activations Density 0.155%

    No Known Activations