© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20683
    Prev
    Next
    INDEX
    Explanations

    square

    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
    满载
    -0.08
    ä»İä»ĸ
    -0.07
     Lama
    -0.07
    alap
    -0.07
    æµģæ°´
    -0.07
    .splitext
    -0.06
    ained
    -0.06
    маÑı
    -0.06
    riv
    -0.06
    çĸĬ
    -0.06
    POSITIVE LOGITS
    ặn
    0.08
    NotFoundException
    0.08
    ocab
    0.07
    稳
    0.07
    _charset
    0.07
    Indexes
    0.07
    à¦ļার
    0.07
     passwords
    0.07
    Charset
    0.07
    _mirror
    0.07
    Activations Density 0.003%

    No Known Activations