© 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. 19058
    Prev
    Next
    INDEX
    Explanations

    Skiing and outdoor activities

    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
    æį§
    -0.12
    lab
    -0.10
    æĮ¥
    -0.09
    å±ŀ
    -0.09
    _HT
    -0.09
    楼ä¸Ĭ
    -0.09
    çĩĶ
    -0.09
    ledo
    -0.09
    çĥĽ
    -0.09
    æ±ģ
    -0.08
    POSITIVE LOGITS
    æ»ijéĽª
    0.15
    è¶Ĭéĩİ
    0.11
    æij©æīĺ
    0.11
    æijĶ
    0.11
    蹦
    0.11
    åľ°å½¢
    0.10
    æij©æīĺ车
    0.10
    æİ¢éĻ©
    0.10
     Ski
    0.10
    çĻ»å±±
    0.10
    Activations Density 0.156%

    No Known Activations