© 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. 31411
    Prev
    Next
    INDEX
    Explanations

    across two terminals

    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
    utu
    -0.09
    çļĦèĦļæŃ¥
    -0.07
    è¶Ł
    -0.06
     Ev
    -0.06
    ÑĥÑĩ
    -0.06
     lùi
    -0.06
     rayon
    -0.06
     Lag
    -0.06
    Ev
    -0.06
    ç¿Ķ
    -0.06
    POSITIVE LOGITS
    -span
    0.09
     pandang
    0.08
     paraz
    0.08
    .between
    0.08
     terminals
    0.08
    rand
    0.08
     span
    0.08
    禧
    0.07
    rive
    0.07
    vida
    0.07
    Activations Density 0.014%

    No Known Activations