© 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. 34205
    Prev
    Next
    INDEX
    Explanations

    refraction

    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
    fredo
    -0.10
    quiera
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    еÑĩÑĮ
    -0.07
    keiten
    -0.07
     Europeo
    -0.07
    zinho
    -0.07
    owed
    -0.07
    à¸Ķาย
    -0.07
    iseaux
    -0.07
    POSITIVE LOGITS
    /ref
    0.09
    edor
    0.08
    alcon
    0.08
    iation
    0.07
    tros
    0.07
    abel
    0.07
    ponsible
    0.07
    vény
    0.07
    ãģİ
    0.07
    jord
    0.07
    Activations Density 0.011%

    No Known Activations