© 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. 13125
    Prev
    Next
    INDEX
    Explanations

    Prakt, dis, motor, blood, Log, anemia, ant

    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
    orada
    -0.09
    ouser
    -0.08
    ydd
    -0.08
    uchs
    -0.07
    unya
    -0.07
    unci
    -0.07
     gär
    -0.07
     دÙħØ´
    -0.07
    &m
    -0.07
    eps
    -0.07
    POSITIVE LOGITS
    erot
    0.06
    hol
    0.06
    tern
    0.06
    è°´
    0.06
    糸
    0.06
    æĭ¬
    0.06
    ãģĵãģĿ
    0.06
    er
    0.06
    åĨ²
    0.06
    èį·
    0.05
    Activations Density 0.080%

    No Known Activations