© 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. 47567
    Prev
    Next
    INDEX
    Explanations

    geographical place names

    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
    kilde
    -0.07
    apy
    -0.07
    ovy
    -0.07
    æ§Ľ
    -0.07
    uson
    -0.07
    Æ¡
    -0.07
    Ñİд
    -0.07
    _declaration
    -0.07
    hout
    -0.07
    idos
    -0.07
    POSITIVE LOGITS
    uant
    0.08
    §
    0.07
    åĮĸæĪIJ
    0.07
    mio
    0.06
    /pm
    0.06
    »
    0.06
    amat
    0.06
    nix
    0.06
     Matters
    0.06
    LOPT
    0.06
    Activations Density 0.036%

    No Known Activations