© 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. 18735
    Prev
    Next
    INDEX
    Explanations

    hydraulic braking systems

    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
    hood
    -0.11
    hely
    -0.10
     pilota
    -0.08
    oard
    -0.08
    izen
    -0.08
    piece
    -0.08
    eworthy
    -0.08
    ##_
    -0.08
    æī¬æī¬
    -0.08
    зна
    -0.07
    POSITIVE LOGITS
    raul
    0.07
    abras
    0.07
    -powered
    0.07
    oraf
    0.07
    ä¸ĬæĿ¥è¯´
    0.06
    manent
    0.06
    ç¿»äºĨ
    0.06
    สà¹Į
    0.06
    rawer
    0.06
    ÙĦÙĬ
    0.06
    Activations Density 0.033%

    No Known Activations