© 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. 27546
    Prev
    Next
    INDEX
    Explanations

    css properties

    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
    Ĩ
    -0.08
    å°ıéĽª
    -0.08
    بارÙĩ
    -0.08
    йÑģ
    -0.07
    èĢ¿èĢ¿
    -0.07
    å·®
    -0.07
    лове
    -0.07
    pera
    -0.07
    è¡į
    -0.07
    åijĨ
    -0.07
    POSITIVE LOGITS
    ulas
    0.07
     version
    0.06
    èĻ«
    0.06
    èŁ²
    0.06
    çŃ¹
    0.06
    ัà¸ķ
    0.06
    çĬ¹
    0.06
    _version
    0.06
    =
    0.06
    alas
    0.06
    Activations Density 0.002%

    No Known Activations