© 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. 40371
    Prev
    Next
    INDEX
    Explanations

    question mark followed by word

    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
    inet
    -0.07
    icol
    -0.06
    éĽĦ
    -0.06
    èįī
    -0.06
    åĶ
    -0.06
    face
    -0.06
    ä¹ĥèĩ³
    -0.06
    Ĵ
    -0.06
    ä¼ĺéĢī
    -0.06
    t
    -0.06
    POSITIVE LOGITS
    (#)
    0.08
    åīį款
    0.07
    _CSR
    0.07
    Ñĩина
    0.07
    /AFP
    0.07
    bench
    0.07
    .–
    0.07
    bern
    0.07
    ãĥijãĥ¼ãĥĪ
    0.07
    naires
    0.07
    Activations Density 0.001%

    No Known Activations