© 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. 13320
    Prev
    Next
    INDEX
    Explanations

    numbers followed by text

    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
    olec
    -0.07
    沦
    -0.06
    kop
    -0.06
    elos
    -0.06
    ango
    -0.06
    ated
    -0.06
    ä¸ĩéĩĮ
    -0.06
    enan
    -0.06
    AG
    -0.06
    鸣
    -0.06
    POSITIVE LOGITS
    setContent
    0.08
    ROUND
    0.08
    stile
    0.08
    ffffffff
    0.08
    á»ĭn
    0.08
    ifice
    0.07
    è´¹çŃī
    0.07
    "]="
    0.07
    Finder
    0.07
     asem
    0.07
    Activations Density 0.075%

    No Known Activations