© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14899
    Prev
    Next
    INDEX
    Explanations

    code syntax: list, colon, brackets

    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
    _NB
    -0.08
    -toggler
    -0.07
    ç§ĭ鼨
    -0.06
    æĥħçIJĨ
    -0.06
    |max
    -0.06
     Vieira
    -0.06
    ]["
    -0.06
    Ľ
    -0.06
    åĪĽå»ºå·¥ä½ľ
    -0.06
    çļĦ积æŀģæĢ§
    -0.06
    POSITIVE LOGITS
    pee
    0.08
    pees
    0.08
    å°Ĭ
    0.08
    ä¸Ī
    0.08
     (),
    0.07
     ?,
    0.07
     {},
    0.07
    è¿İ
    0.07
    acon
    0.07
    аÑģа
    0.07
    Activations Density 0.016%

    No Known Activations