© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20815
    Prev
    Next
    INDEX
    Explanations

    logic conjunction and enumeration

    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
    ken
    -0.07
    å¾Īå¤ļéĹ®é¢ĺ
    -0.07
    ice
    -0.07
    å±
    -0.07
    cy
    -0.06
    avy
    -0.06
    ï
    -0.06
    uid
    -0.06
    /MIT
    -0.06
    ble
    -0.06
    POSITIVE LOGITS
    äºĨä¸Ģä¸Ŀ
    0.08
    رس
    0.07
    ä¸įè¨Ģ
    0.07
    ιÏī
    0.07
    人åijĺè§Ħ模
    0.07
    ackers
    0.07
    ä»ĸäºĨ
    0.07
    éĩľ
    0.07
    atica
    0.07
    äºĨä¸ĢèĤ¡
    0.07
    Activations Density 0.075%

    No Known Activations