© 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. 19078
    Prev
    Next
    INDEX
    Explanations

    academic citations with page 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
    undy
    -0.09
    edList
    -0.08
     Colonia
    -0.08
    thood
    -0.08
    stwo
    -0.08
    chaft
    -0.08
    ä¹ĭæģĭ
    -0.07
    zuh
    -0.07
    iculum
    -0.07
    shaw
    -0.07
    POSITIVE LOGITS
     http
    0.06
    amine
    0.06
    9
    0.06
    arin
    0.06
    ème
    0.06
    ar
    0.06
    7
    0.06
    综åIJĪè¿IJçĶ¨
    0.06
    //[
    0.06
     Various
    0.06
    Activations Density 0.008%

    No Known Activations