© 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. 19229
    Prev
    Next
    INDEX
    Explanations

    band archives part

    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
    延年
    -0.07
    pp
    -0.07
    èĮī
    -0.07
    eing
    -0.07
    åĩłå¤©çļĦ
    -0.07
    /original
    -0.06
    è¾Ħ
    -0.06
    æ¯ıåŃ¦æľŁ
    -0.06
    çīĩçīĩ
    -0.06
    pair
    -0.06
    POSITIVE LOGITS
    åĮħæĭ¬
    0.13
    åĮħæĭ¬äºĨ
    0.12
     entirety
    0.11
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.11
    è¿ĺåĮħæĭ¬
    0.11
    åħ¶ä¸ŃåĮħæĭ¬
    0.11
     entire
    0.10
    ä¸ŃçļĦæīĢæľī
    0.10
     вклÑİÑĩаÑı
    0.10
    including
    0.10
    Activations Density 0.010%

    No Known Activations