© 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. 40585
    Prev
    Next
    INDEX
    Explanations

    radius, curvature, curves

    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
     Pawn
    -0.07
     Bush
    -0.07
    èįī丼
    -0.07
    éľĨ
    -0.07
    Bush
    -0.07
    å¼Ģæľº
    -0.06
    Gew
    -0.06
    ç¬ĭ
    -0.06
     thrift
    -0.06
    ãĤ¶ãĥ¼
    -0.06
    POSITIVE LOGITS
    -radius
    0.13
    åįĬå¾Ħ
    0.12
     radius
    0.12
    缴å¾Ħ
    0.12
    Radius
    0.11
     Radius
    0.11
    radius
    0.11
     curvature
    0.10
    弧度
    0.10
    (radius
    0.10
    Activations Density 0.012%

    No Known Activations