© 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. 55434
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    occas
    -0.07
    acci
    -0.07
    неж
    -0.07
    legg
    -0.07
    åīįè¾Ī
    -0.07
    esan
    -0.07
    ÏĦÎŃÏģ
    -0.07
    \\/
    -0.07
    ontre
    -0.07
     лен
    -0.06
    POSITIVE LOGITS
    LIC
    0.07
    å°¼äºļ
    0.07
    ÅĤoÅĽ
    0.06
    marks
    0.06
    æı£
    0.06
    æľ¬ç«Ļ
    0.06
    nds
    0.06
    ilib
    0.06
    emani
    0.06
    æĬĢæľ¯çĽijçĿ£
    0.06
    Activations Density 0.766%

    No Known Activations