© 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. 60625
    Prev
    Next
    INDEX
    Explanations

    code delimiters and numbers

    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
    umont
    -0.07
    ½
    -0.06
    -0.06
    èĿĩ
    -0.06
    Ùį
    -0.06
    Ùij
    -0.06
    åı²ä¸Ĭ
    -0.06
    |
    -0.05
    erne
    -0.05
    äºĽ
    -0.05
    POSITIVE LOGITS
    porter
    0.08
    utdown
    0.08
    _mux
    0.08
    еÑģÑģ
    0.08
    øm
    0.08
    ouverte
    0.07
    atora
    0.07
     αÏĢοÏĨ
    0.07
    кÑĢÑĥг
    0.07
    äck
    0.07
    Activations Density 0.041%

    No Known Activations