© 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. 5234
    Prev
    Next
    INDEX
    Explanations

    movement and arrival

    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
    å±ĬæŶ
    -0.11
    äºĭåħĪ
    -0.10
    è¿Ľåĩº
    -0.09
    çĬģ
    -0.09
    Ñģел
    -0.08
    æĪ´çĿĢ
    -0.08
    èĢ½è¯¯
    -0.08
    å¾Ĺä½ı
    -0.08
    大大å°ıå°ı
    -0.08
    å¿ĥçĸ¼
    -0.08
    POSITIVE LOGITS
    å¡į
    0.10
     ТÑĥÑĢ
    0.09
    é¢Ľ
    0.09
    è°ĥæŁ¥æĺ¾ç¤º
    0.09
    ä¸ĢæŃ¥
    0.09
    dux
    0.08
    âĵĺ
    0.08
    getDb
    0.08
    æģ¯
    0.08
    身边
    0.08
    Activations Density 0.091%

    No Known Activations