© 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. 28324
    Prev
    Next
    INDEX
    Explanations

    closest to

    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
    Flow
    -0.08
     flow
    -0.08
    FLOW
    -0.08
     Flow
    -0.07
     scratching
    -0.07
    æµģ转
    -0.07
    çĶ·åĦ¿
    -0.07
    主è¦ģ产åĵģ
    -0.07
    ä¹IJæĦı
    -0.07
    flow
    -0.07
    POSITIVE LOGITS
     distance
    0.12
     closest
    0.12
    è·ĿéĽ¢
    0.12
     distances
    0.11
    è·Ŀ离
    0.11
    çļĦè·Ŀ离
    0.11
    nearest
    0.11
    distance
    0.11
     Distance
    0.11
    -distance
    0.11
    Activations Density 0.017%

    No Known Activations