© 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. 49412
    Prev
    Next
    INDEX
    Explanations

    spot, status, meeting, geo

    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
    หà¸Ļà¹īาà¸Ļีà¹ī
    -0.07
    æĿŃ
    -0.07
    cha
    -0.07
     Puglia
    -0.07
    cas
    -0.07
    ลาส
    -0.07
    енеÑĢа
    -0.07
    Ñħа
    -0.07
    è°¦èĻļ
    -0.07
    CHA
    -0.07
    POSITIVE LOGITS
    iat
    0.07
    iet
    0.07
    ip
    0.07
    é¡¿
    0.06
    ึà¸ĩ
    0.06
    çķħæĥ³
    0.06
    iam
    0.06
     Clem
    0.06
     genu
    0.06
    iot
    0.06
    Activations Density 0.780%

    No Known Activations