© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2283
    Prev
    Next
    INDEX
    Explanations

    length measurement related words

    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
    ething
    -0.08
    plen
    -0.08
    éķ¿èħ¿
    -0.07
    ÙĮÙij
    -0.07
    orthy
    -0.07
    ulkan
    -0.07
    ellino
    -0.07
    akwa
    -0.07
    angkal
    -0.07
     nhiêu
    -0.07
    POSITIVE LOGITS
    ening
    0.13
    wise
    0.11
    ened
    0.11
    evity
    0.09
    itude
    0.09
    uage
    0.09
    itud
    0.09
    ITUDE
    0.08
    اÙĨÛĮ
    0.08
    agoon
    0.08
    Activations Density 0.022%

    No Known Activations