© 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. 32100
    Prev
    Next
    INDEX
    Explanations

    arcs, rotation, angles

    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
    é¢ł
    -0.07
    åij±åij±
    -0.07
    å±Ĥ级
    -0.07
     disag
    -0.07
    ague
    -0.07
    inho
    -0.07
    åħµçİĭ
    -0.07
    Rocket
    -0.07
     cave
    -0.07
    vej
    -0.07
    POSITIVE LOGITS
    ë§Įíģ¼
    0.10
     radians
    0.10
    度æķ°
    0.10
     rotation
    0.09
    弧度
    0.09
    .radians
    0.09
    ä¸Ģ转
    0.09
    rotation
    0.08
     rotations
    0.08
     ë§Įíģ¼
    0.08
    Activations Density 0.009%

    No Known Activations