© 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. 2093
    Prev
    Next
    INDEX
    Explanations

    else or other

    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
     demais
    -0.09
     meisten
    -0.08
    aler
    -0.08
    ä¸Ģæ´¾
    -0.08
    adop
    -0.08
    ergestellt
    -0.08
    alia
    -0.07
     others
    -0.07
    illen
    -0.07
    áu
    -0.07
    POSITIVE LOGITS
    isable
    0.08
    -fashioned
    0.07
    uffs
    0.07
    esis
    0.07
    UDIO
    0.07
    levant
    0.07
    than
    0.06
    (es
    0.06
    ëĿ¼ëıĦ
    0.06
    oled
    0.06
    Activations Density 0.045%

    No Known Activations