© 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. 3149
    Prev
    Next
    INDEX
    Explanations

    mathematical and code symbols

    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
    âĢij
    -0.09
    ='./
    -0.06
    为ä¿Ŀéļľ
    -0.06
    è°ĭåıijå±ķ
    -0.06
    ../../../
    -0.06
    ËĩËĩ
    -0.06
    第äºĮçĻ¾éĽ¶
    -0.06
    èĩªå®¶
    -0.06
    _RC
    -0.06
    iach
    -0.06
    POSITIVE LOGITS
     ‘’
    0.08
     Feinstein
    0.08
     industr
    0.07
    çĽ¾çīĮ
    0.07
    ç«¥éŀĭ
    0.07
    éĤ
    0.07
     Anthem
    0.07
    ayload
    0.07
    icine
    0.07
    ultat
    0.07
    Activations Density 0.004%

    No Known Activations