© 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. 25268
    Prev
    Next
    INDEX
    Explanations

    value of calculations

    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
    anda
    -0.07
    st
    -0.07
    g
    -0.06
    eds
    -0.06
    aq
    -0.06
    ut
    -0.06
    éĩįè¦ģæĢ§
    -0.06
    ed
    -0.06
    'o
    -0.06
    to
    -0.06
    POSITIVE LOGITS
    InMillis
    0.08
    ampler
    0.08
    åĽłæѤèĢĮ
    0.08
     recurs
    0.07
    ÃŃas
    0.07
    iali
    0.07
    eree
    0.07
     riêng
    0.07
    voke
    0.07
    nex
    0.07
    Activations Density 0.063%

    No Known Activations