© 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. 31113
    Prev
    Next
    INDEX
    Explanations

    acceleration and accelerometer

    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
    sworth
    -0.09
    полÑĥ
    -0.08
    åįİåĽ¾
    -0.08
    Цен
    -0.08
    _exceptions
    -0.07
    è·¯éĢı
    -0.07
    žil
    -0.07
    _COLL
    -0.07
    contri
    -0.07
    óÅĤ
    -0.07
    POSITIVE LOGITS
    åĬłéĢŁåº¦
    0.13
     acceleration
    0.12
     acceler
    0.11
    Acceleration
    0.11
    åĬłéĢŁ
    0.11
     Acceler
    0.10
    accel
    0.10
    .accel
    0.09
     jerk
    0.09
     aceler
    0.09
    Activations Density 0.004%

    No Known Activations