© 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. 40608
    Prev
    Next
    INDEX
    Explanations

    tokens suggesting specific suffixes or endings

    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
    REAK
    -0.07
    wad
    -0.07
    oty
    -0.07
    engt
    -0.07
     Laud
    -0.07
    _learn
    -0.06
    boli
    -0.06
    ucht
    -0.06
    ourt
    -0.06
     unl
    -0.06
    POSITIVE LOGITS
    -worthy
    0.08
    adamente
    0.07
    ationally
    0.06
    orest
    0.06
    åįĩåĪĿ
    0.06
    ses
    0.06
    orer
    0.06
    AZE
    0.06
    емо
    0.06
    rolls
    0.06
    Activations Density 0.069%

    No Known Activations