© 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. 19613
    Prev
    Next
    INDEX
    Explanations

    .hibernate or .validator

    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
    emes
    -0.08
    åıĸçļĦ
    -0.07
    ruk
    -0.07
    客è¿IJç«Ļ
    -0.07
    https
    -0.07
     http
    -0.07
    ä¸į移
    -0.07
    eres
    -0.07
     https
    -0.06
    ä¸Ńæļij
    -0.06
    POSITIVE LOGITS
    odem
    0.07
    ullo
    0.07
    udem
    0.07
    çł´å¤©
    0.07
    osg
    0.07
    éºŁ
    0.07
    $j
    0.07
    ulumi
    0.07
    åIJĪ家
    0.07
    rese
    0.07
    Activations Density 0.022%

    No Known Activations