© 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. 56471
    Prev
    Next
    INDEX
    Explanations

    small or weak quantities

    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
    erot
    -0.08
    毫ä¸į
    -0.08
    SETTING
    -0.08
    ÐŃС
    -0.08
    usus
    -0.08
    continent
    -0.08
    ĥĿ
    -0.07
    ulut
    -0.07
    ully
    -0.07
    IDD
    -0.07
    POSITIVE LOGITS
     enough
    0.11
     Enough
    0.08
     (<
    0.08
    /small
    0.08
    coli
    0.08
     genug
    0.08
    Enough
    0.07
    (<
    0.07
     rel
    0.06
    hom
    0.06
    Activations Density 0.015%

    No Known Activations