© 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. 57881
    Prev
    Next
    INDEX
    Explanations

    entities, identifiers, or contexts

    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
    éĩİ
    -0.07
    uah
    -0.07
    æĺ§
    -0.07
    èľ
    -0.07
    åıĮéĩį
    -0.06
    valg
    -0.06
    大为
    -0.06
    /tiny
    -0.06
    ¾
    -0.06
    è´
    -0.06
    POSITIVE LOGITS
    orgia
    0.08
    ibbon
    0.08
    ogramm
    0.07
    å¤ļç§įæĸ¹å¼ı
    0.07
    ulary
    0.07
    IFO
    0.06
    åįģä¸īç«ł
    0.06
    pery
    0.06
    çļĦè¿ĻäºĽ
    0.06
    èİĬ
    0.06
    Activations Density 0.107%

    No Known Activations