© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12952
    Prev
    Next
    INDEX
    Explanations

    Van Horn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å½ĵçĦ¶æĺ¯
    -0.08
    æ°¸éģł
    -0.08
    æĹłçĸij
    -0.08
     unmistak
    -0.08
     ëĭ¹ìĹ°íŀĪ
    -0.07
     nada
    -0.07
    åºŁè¯Ŀ
    -0.07
    æĹłçĸijæĺ¯
    -0.07
    ä¸į认è¯Ĩ
    -0.07
    没æľīä»»ä½ķ
    -0.07
    POSITIVE LOGITS
    èĻ½æľī
    0.14
    åľ¨ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    0.12
    æŁIJç§įç¨ĭ度ä¸Ĭ
    0.12
    èĻ½çĦ¶æľī
    0.11
     potentially
    0.11
    æľīä¸Ģå®ļçļĦ
    0.11
    æľªå¿ħ
    0.11
     partly
    0.11
    åħ·æľīä¸Ģå®ļçļĦ
    0.10
    èĻ½
    0.10
    Activations Density 0.006%

    No Known Activations