© 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. 25793
    Prev
    Next
    INDEX
    Explanations

    locations and times

    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
    ¨
    -0.08
    å¾ĢæľŁåĽŀ顾
    -0.07
    Arm
    -0.06
    srv
    -0.06
    å¥Īä½ķ
    -0.06
    endis
    -0.06
    çİīå±±
    -0.06
    åı«çĿĢ
    -0.06
    ä¾Ŀå±±
    -0.06
    容
    -0.06
    POSITIVE LOGITS
    ãĥįãĥ«
    0.08
    inna
    0.07
    плÑİ
    0.07
    .exec
    0.07
    elv
    0.07
    agra
    0.07
    AuthProvider
    0.07
    ÑĤÑĢÑĥ
    0.07
    .instance
    0.07
    plex
    0.07
    Activations Density 0.018%

    No Known Activations