© 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. 61653
    Prev
    Next
    INDEX
    Explanations

    communication styles and jargon

    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
    磼
    -0.07
    ahan
    -0.07
    好åIJİ
    -0.06
    çķĻæľī
    -0.06
    /per
    -0.06
    è¯ģæį®è¯ģæĺİ
    -0.06
     plotted
    -0.06
    _hw
    -0.06
    åıĹ
    -0.06
    _via
    -0.06
    POSITIVE LOGITS
    argon
    0.09
     bullshit
    0.09
     unnecessarily
    0.08
    aren
    0.08
    |#
    0.07
    檻
    0.07
    å°½éĩıå°ij
    0.07
    alatan
    0.07
    ä¸Ģç½ij
    0.07
     unnecessary
    0.07
    Activations Density 0.001%

    No Known Activations