© 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. 44941
    Prev
    Next
    INDEX
    Explanations

    list declarations and variable assignments

    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
    dam
    -0.07
     latin
    -0.06
    phu
    -0.06
    ä¾µ
    -0.06
    cht
    -0.06
     losers
    -0.06
    æĺŁæľŁå¤©
    -0.06
    áz
    -0.06
    empor
    -0.06
    æĮĩåIJij
    -0.06
    POSITIVE LOGITS
    ilver
    0.07
    &type
    0.07
    utta
    0.07
    á»ħ
    0.07
    uls
    0.07
    æIJľæŁ¥
    0.07
    odash
    0.07
     أر
    0.07
    uito
    0.07
     xuyên
    0.07
    Activations Density 0.104%

    No Known Activations