© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9077
    Prev
    Next
    INDEX
    Explanations

    agrees, affirmative responses

    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
     ØŃرÙģ
    -0.08
    ÑĢÑı
    -0.07
    ern
    -0.07
    åĽĬ
    -0.07
    åłĤåłĤ
    -0.07
    erson
    -0.06
    åıĬåħ¶
    -0.06
     asyncio
    -0.06
     sourceMappingURL
    -0.06
    asl
    -0.06
    POSITIVE LOGITS
    htable
    0.08
    åĬªåĬĽå®ŀçİ°
    0.08
    ç¢İçļĦ
    0.08
    igu
    0.08
    duc
    0.07
     vul
    0.07
    ĵ¨
    0.07
    letes
    0.07
    SWG
    0.07
    alian
    0.07
    Activations Density 0.003%

    No Known Activations