© 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. 63659
    Prev
    Next
    INDEX
    Explanations

    features and their descriptions

    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
    ulation
    -0.09
    åĽŀäºĭ
    -0.08
    -fashioned
    -0.08
    erton
    -0.07
    IMUM
    -0.07
    ander
    -0.07
    isper
    -0.07
    Ø©
    -0.07
    ../
    -0.07
    soever
    -0.07
    POSITIVE LOGITS
    tte
    0.11
    ttes
    0.11
    ен
    0.10
    less
    0.10
    rakt
    0.09
    lessly
    0.09
     prominently
    0.08
    ancis
    0.08
    人åħ³æ³¨
    0.08
    lise
    0.08
    Activations Density 0.042%

    No Known Activations