© 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. 42110
    Prev
    Next
    INDEX
    Explanations

    special case keywords

    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
     Pane
    -0.06
    ::$
    -0.06
    _basename
    -0.06
    åIJĿ
    -0.06
    éli
    -0.05
    én
    -0.05
    _REGISTRY
    -0.05
    PrototypeOf
    -0.05
    æ½¢
    -0.05
    ves
    -0.05
    POSITIVE LOGITS
    %C
    0.09
    ä½Ĩèĩ³å°ij
    0.09
    \'\
    0.08
    ])(
    0.08
    ï¼ļ%
    0.08
    %**
    0.08
    çĻ»å½ķæŁ¥çľĭ
    0.08
    /--
    0.08
    请æĭ¨æīĵ
    0.08
    }\"
    0.07
    Activations Density 0.403%

    No Known Activations