© 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. 63617
    Prev
    Next
    INDEX
    Explanations

    gas turbine

    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
    íĹĺ
    -0.08
    ìķ¼
    -0.08
    jÅ¡ÃŃ
    -0.08
    à»ī
    -0.08
    skraft
    -0.07
    scher
    -0.07
     اÙĦغذائÙĬ
    -0.07
    æŀĿèĬ±
    -0.07
    ighton
    -0.07
    ì°į
    -0.07
    POSITIVE LOGITS
    ified
    0.10
    ification
    0.09
    ़
    0.09
    roupe
    0.08
    oble
    0.08
    borne
    0.08
    ually
    0.08
    ifier
    0.08
    ilent
    0.08
    ateway
    0.08
    Activations Density 0.024%

    No Known Activations