© 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. 14743
    Prev
    Next
    INDEX
    Explanations

    get;

    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
    )':
    -0.07
    »:
    -0.07
    ]:
    -0.07
    `:
    -0.07
    )):
    -0.07
    '):
    -0.06
    ):
    -0.06
    ARIO
    -0.06
    ä¸įèĥľ
    -0.06
     Siap
    -0.06
    POSITIVE LOGITS
    beh
    0.08
    xada
    0.07
    âķIJâķIJâķIJâķIJ
    0.07
    ë¡Ŀ
    0.07
     Travail
    0.07
    æ¯Ķåݻ年åIJĮæľŁ
    0.06
    волÑĮ
    0.06
    иÑģк
    0.06
    éĩĮ头
    0.06
    åıģ
    0.06
    Activations Density 0.025%

    No Known Activations