© 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. 23899
    Prev
    Next
    INDEX
    Explanations

    describing tone or style

    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
    åѤçĭ¬çļĦ
    -0.08
    çļĦå¿ĥæĢĿ
    -0.08
    ignano
    -0.08
    çİ·
    -0.07
    lingen
    -0.07
    úz
    -0.07
    éĢ¼çľŁçļĦ
    -0.07
    mares
    -0.07
    гÑĢе
    -0.07
    ilon
    -0.07
    POSITIVE LOGITS
     slightly
    0.08
    ent
    0.07
     exploration
    0.07
     neutral
    0.07
     informative
    0.07
    aptor
    0.07
    çķ¥å¸¦
    0.07
     explor
    0.07
     Neutral
    0.06
     explanatory
    0.06
    Activations Density 0.006%

    No Known Activations