© 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. 43711
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

    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
    irk
    -0.06
    ç½ijé¦ĸ页
    -0.06
    acy
    -0.06
     dep
    -0.06
    ignan
    -0.06
    ↵
    -0.06
    ç´§ç´§åľ°
    -0.06
    aka
    -0.06
     mathematical
    -0.06
    ä»¿ä½Ľæĺ¯
    -0.05
    POSITIVE LOGITS
    à¤Ĺत
    0.08
    fertig
    0.08
     Gallup
    0.08
    BYTE
    0.08
    ä¿ĬæĿ°
    0.08
    æ¾İ
    0.08
    anea
    0.07
    ENCI
    0.07
    å®Įç»ĵ
    0.07
    æľīäºĽäºĭ
    0.07
    Activations Density 0.005%

    No Known Activations