© 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. 11298
    Prev
    Next
    INDEX
    Explanations

    informs copyright holders

    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
    IMUM
    -0.11
    ÑİÑĤ
    -0.11
    ation
    -0.10
    ivism
    -0.10
    Ø©
    -0.09
     itself
    -0.08
    eur
    -0.08
    urna
    -0.08
    emment
    -0.08
    o
    -0.08
    POSITIVE LOGITS
     themselves
    0.18
    åIJĦèĩªçļĦ
    0.13
    atically
    0.13
     berdua
    0.12
    hips
    0.11
     thems
    0.11
    åIJĦèĩª
    0.11
     Ø£ÙĨÙģسÙĩÙħ
    0.10
     respective
    0.10
     stessi
    0.10
    Activations Density 0.251%

    No Known Activations