© 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. 31013
    Prev
    Next
    INDEX
    Explanations

    spaceship rotation

    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
    æīĭèħķ
    -0.09
     dep
    -0.09
    梦å¢ĥ
    -0.09
    æįı
    -0.08
    楼梯
    -0.08
    dep
    -0.08
    å¸
    -0.08
    渴
    -0.08
    checker
    -0.08
    å·²ç»ıå¼Ģå§ĭ
    -0.08
    POSITIVE LOGITS
    éĺ²å¾¡
    0.10
    åĬŁçİĩ
    0.10
    åĨĽå·¥
    0.09
    çĤ¬
    0.09
    isy
    0.09
    èĢģ大
    0.09
    æµ·ä¸Ĭ
    0.09
    _PRIMARY
    0.09
    à¸Ĥà¸Ļ
    0.09
    .toDouble
    0.08
    Activations Density 0.081%

    No Known Activations