© 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. 57102
    Prev
    Next
    INDEX
    Explanations

    tends to infinity

    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
    лада
    -0.08
    ä¸İéĿŀ
    -0.08
    ciata
    -0.07
     müs
    -0.07
    ette
    -0.07
    azzo
    -0.07
     fiquei
    -0.07
    äºijä¸Ĭ
    -0.07
    åĪ©çī©
    -0.07
    amakan
    -0.07
    POSITIVE LOGITS
    иÑģло
    0.07
    ymp
    0.07
    erview
    0.07
    igin
    0.06
    thon
    0.06
    otics
    0.06
    _snap
    0.06
    çĩ
    0.06
    Å«
    0.06
    uren
    0.06
    Activations Density 0.005%

    No Known Activations