© 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. 29107
    Prev
    Next
    INDEX
    Explanations

    force, impulse, action

    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
    _REGION
    -0.08
    å·´æİĮ
    -0.07
    ynth
    -0.07
    zone
    -0.07
    region
    -0.07
     regional
    -0.07
     Patio
    -0.07
    alue
    -0.07
    åĮºåŁŁæĢ§
    -0.07
     régional
    -0.07
    POSITIVE LOGITS
    ambu
    0.09
     trajectory
    0.09
    轨迹
    0.08
     GPS
    0.08
    çīµå¼ķ
    0.08
    trajectory
    0.07
     trajectories
    0.07
    GPS
    0.07
     equipped
    0.07
    ulling
    0.07
    Activations Density 0.003%

    No Known Activations