© 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. 3633
    Prev
    Next
    INDEX
    Explanations

    BoshqÄģbak, Maohi (MÄģ’ohi, PÄģ’Ä«n, Qal”ehsi, dÄģnu, dÄģnu, ShowhÄģn-e, ‘OlyÄģ, KÄ«lauea, anattÄģ, SayyÄģr, á¹£mare

    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
    s
    -0.11
    ation
    -0.10
    ed
    -0.09
    m
    -0.08
    t
    -0.08
    ness
    -0.08
    p
    -0.07
    n
    -0.07
    mals
    -0.07
    l
    -0.07
    POSITIVE LOGITS
    er
    0.14
    erstand
    0.09
    culate
    0.09
    erma
    0.09
    ×ķר×Ļ×Ŀ
    0.09
    ername
    0.09
    ë¦Ħ
    0.08
    liness
    0.08
    oppable
    0.08
    à§įড
    0.08
    Activations Density 0.018%

    No Known Activations