© 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. 43791
    Prev
    Next
    INDEX
    Explanations

    author, multipart

    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
    leter
    -0.08
    ordia
    -0.07
    ynie
    -0.07
    utam
    -0.07
    rawy
    -0.07
     оÑĤо
    -0.07
    ny
    -0.07
    ence
    -0.07
    aut
    -0.07
    yas
    -0.07
    POSITIVE LOGITS
    mara
    0.07
    anca
    0.07
    é£İçļĦ
    0.07
    sud
    0.06
    ãģ¾ãģĦ
    0.06
    etrie
    0.06
    afia
    0.06
    udos
    0.06
    brick
    0.06
    ofilm
    0.06
    Activations Density 0.047%

    No Known Activations