© 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. 63172
    Prev
    Next
    INDEX
    Explanations

    conductivity

    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
    allax
    -0.08
     singleton
    -0.07
    å®īè¾¾
    -0.07
    ppard
    -0.07
    (Android
    -0.07
    moi
    -0.07
    dddd
    -0.07
     Ving
    -0.07
    è¿Ľè¡Įè°ĥæķ´
    -0.06
    alama
    -0.06
    POSITIVE LOGITS
    ä½İ温
    0.10
    åĨ°
    0.09
    æµĭ温
    0.09
    ikel
    0.09
     bÄĥng
    0.09
    è¶ħ导
    0.09
     ice
    0.09
    çļĦåĨ°
    0.08
    bras
    0.08
    笹
    0.08
    Activations Density 0.017%

    No Known Activations