© 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. 9611
    Prev
    Next
    INDEX
    Explanations

    modelmodel 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
    çĽĨ
    -0.07
    enske
    -0.07
    容积
    -0.07
     formula
    -0.06
    -0.06
    cdf
    -0.06
     pl
    -0.06
    менÑĤиÑĢов
    -0.06
    ken
    -0.06
     Horton
    -0.06
    POSITIVE LOGITS
     дÑĢе
    0.09
    Elec
    0.09
    _ticks
    0.08
    격
    0.08
     tunes
    0.08
    _tick
    0.08
    _reordered
    0.08
    ingang
    0.08
    åĥļ
    0.08
    é¹Ĭ
    0.08
    Activations Density 0.013%

    No Known Activations