© 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. 10199
    Prev
    Next
    INDEX
    Explanations

    BT_INFO or similar defines

    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
    à¸Ĺั
    -0.06
    æĭĽæĥ¹
    -0.06
    å®£ä¼łæ´»åĬ¨
    -0.06
    羣å¿ĥ
    -0.06
    _VIRTUAL
    -0.06
    abela
    -0.06
    иÑģÑĤо
    -0.06
    æĥ³å¿µ
    -0.06
    με
    -0.06
    ëŁ½
    -0.06
    POSITIVE LOGITS
    ucha
    0.08
    åIJĮä¸Ĭ
    0.07
    utsch
    0.07
    è¿ĺçĶ¨
    0.07
    赫çĦ¶
    0.07
    å¤©æľº
    0.07
    -vers
    0.07
    thed
    0.06
    è±ģçĦ¶
    0.06
    osse
    0.06
    Activations Density 0.495%

    No Known Activations