© 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. 24277
    Prev
    Next
    INDEX
    Explanations

    of \[word]

    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
    eldo
    -0.08
    /testing
    -0.08
     Freitas
    -0.08
    åĴĮ建设
    -0.07
    èĤ¡ä»½æľīéĻIJåħ¬åı¸
    -0.07
    åıĬéĶĢåĶ®
    -0.07
    zaam
    -0.07
    estand
    -0.07
    ments
    -0.07
     flore
    -0.07
    POSITIVE LOGITS
    -of
    0.14
     of
    0.12
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.10
     de
    0.10
    à¹ģหà¹Īà¸ĩ
    0.10
    _of
    0.09
    ofd
    0.08
    à¸Ĺาà¸ĩà¸ģาร
    0.08
    à¸Ĥà¸Ńà¸ĩà¸Ħวาม
    0.08
     Of
    0.08
    Activations Density 0.549%

    No Known Activations