© 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. 34646
    Prev
    Next
    INDEX
    Explanations

    groups of related entities

    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
    lendir
    -0.09
    erce
    -0.08
    bruck
    -0.08
    uell
    -0.08
    ä¸Ĭä¸İ
    -0.08
    åįĹé£İ
    -0.08
    tral
    -0.07
    ä»»ä½ķåªĴä½ĵ
    -0.07
    amakan
    -0.07
    xico
    -0.07
    POSITIVE LOGITS
    åįķçĭ¬
    0.07
    å¡
    0.06
    éĩĬ
    0.06
    å®
    0.06
    d
    0.06
    å¯Ħ宿
    0.06
     composed
    0.06
    ä½ľçĶ¨
    0.06
     PERMISSION
    0.06
    åįķæĭĽ
    0.06
    Activations Density 0.001%

    No Known Activations