© 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. 43862
    Prev
    Next
    INDEX
    Explanations

    sequence probability nqnn

    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
    Ùħد
    -0.07
    OMO
    -0.07
    verno
    -0.07
    quist
    -0.06
    åī¤
    -0.06
    .isHidden
    -0.06
     Dispatch
    -0.06
    parser
    -0.06
    tem
    -0.06
    bout
    -0.06
    POSITIVE LOGITS
    alur
    0.07
    åı¯æ¢¦
    0.07
    aldo
    0.07
    apul
    0.07
     obv
    0.07
    ásticas
    0.06
    rellas
    0.06
    ciano
    0.06
    alda
    0.06
    rowable
    0.06
    Activations Density 0.002%

    No Known Activations