© 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. 16402
    Prev
    Next
    INDEX
    Explanations

    code diffs with

    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
    ÏĩÏİ
    -0.08
    ieke
    -0.08
    .datab
    -0.07
    avanaugh
    -0.07
    ophon
    -0.07
    ÑħÑĸ
    -0.07
     Kasat
    -0.07
    apolis
    -0.07
     Kemb
    -0.07
    ipper
    -0.07
    POSITIVE LOGITS
    Âł
    0.08
    ë°°
    0.06
    ami
    0.06
    âĢ
    0.06
    çĩķ
    0.06
    ensions
    0.06
    b
    0.06
     Humanities
    0.06
    循
    0.06
    binations
    0.06
    Activations Density 0.018%

    No Known Activations