© 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. 61066
    Prev
    Next
    INDEX
    Explanations

    mean age

    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
    жек
    -0.07
    eia
    -0.06
    Convention
    -0.06
    ceed
    -0.06
    èij
    -0.06
    кÑĥÑĢ
    -0.06
    iori
    -0.06
     Bullet
    -0.06
    /files
    -0.06
    _here
    -0.06
    POSITIVE LOGITS
    ä¸įæľį
    0.09
    sker
    0.09
    æĸ¹å·®
    0.08
    locker
    0.08
    ä»İä»Ĭå¹´
    0.07
    åĸľæĢĴ
    0.07
    SYS
    0.07
    ENDA
    0.07
    å³¥
    0.07
     uncert
    0.07
    Activations Density 0.022%

    No Known Activations