© 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. 24407
    Prev
    Next
    INDEX
    Explanations

    met

    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
    豪
    -0.07
    éħį
    -0.07
    stro
    -0.06
    atr
    -0.06
     nul
    -0.06
    aur
    -0.06
    è½
    -0.06
     brak
    -0.06
    åºı
    -0.06
    èı
    -0.06
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.10
    zeg
    0.08
    wein
    0.07
    åľ¨çº¿æŶéĹ´
    0.07
     Dw
    0.07
    ائÙħ
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    /feed
    0.07
    ês
    0.07
    isse
    0.07
    Activations Density 0.003%

    No Known Activations