© 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. 46055
    Prev
    Next
    INDEX
    Explanations

    non-negative integer or semi-definite

    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
    asma
    -0.07
    æµ·çĩķ
    -0.07
    um
    -0.07
    糸
    -0.07
    å°º
    -0.07
    utin
    -0.07
    ach
    -0.07
     Cair
    -0.07
    ummer
    -0.07
    èĢ¿èĢ¿
    -0.07
    POSITIVE LOGITS
     Seger
    0.08
    ypsum
    0.08
    æŃ»è§Ĵ
    0.07
    ellate
    0.07
    æĹłçĹĽ
    0.07
    ollo
    0.07
    IDOS
    0.07
    鸵
    0.07
     muzzle
    0.07
    èĴ
    0.07
    Activations Density 0.003%

    No Known Activations