© 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. 26152
    Prev
    Next
    INDEX
    Explanations

    diameter and bore size

    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
     Liver
    -0.07
     secular
    -0.07
    å¦Ĥæ½®
    -0.06
     sour
    -0.06
     tenant
    -0.06
     rooftop
    -0.06
    åĬ¨åijĺ
    -0.06
    æĹ©åıijçİ°
    -0.06
    é¡·
    -0.06
    åĮ¾
    -0.06
    POSITIVE LOGITS
     diameter
    0.14
    缴å¾Ħ
    0.14
    å¤ĸå¾Ħ
    0.13
    å¾Ħ
    0.13
     Diameter
    0.12
    iameter
    0.12
     диамеÑĤÑĢом
    0.12
    å¾ij
    0.11
     Durchmesser
    0.11
     taper
    0.11
    Activations Density 0.087%

    No Known Activations