© 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. 12214
    Prev
    Next
    INDEX
    Explanations

    division and citations

    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
    ddit
    -0.06
    麾
    -0.06
    indi
    -0.06
    jn
    -0.06
    strup
    -0.06
    éŀį
    -0.06
    oref
    -0.06
    ä»ĭ
    -0.06
    趣
    -0.06
     contigo
    -0.06
    POSITIVE LOGITS
    åħ¶èº«
    0.08
    avana
    0.07
    imba
    0.07
    wear
    0.07
    çİĩ为
    0.07
    omba
    0.07
    compile
    0.07
    _HEADERS
    0.07
    çĶĺèįī
    0.07
    iog
    0.07
    Activations Density 0.004%

    No Known Activations