© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22799
    Prev
    Next
    INDEX
    Explanations

    transition metal

    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
    oppen
    -0.08
    å¹³éĺ³
    -0.07
    istar
    -0.07
    ?id
    -0.07
     Parch
    -0.07
    ëı
    -0.07
    çŃīåIJĦ项
    -0.07
    ç´Ĺ
    -0.07
    åľ¨åĨľæĿij
    -0.07
    ä½ĻæĿŃ
    -0.07
    POSITIVE LOGITS
     metals
    0.12
     меÑĤалл
    0.09
     metal
    0.09
     Metals
    0.09
    è¿ĩ渡
    0.09
     metall
    0.09
    metal
    0.09
     Metal
    0.08
    éĩijå±ŀ
    0.08
    éĩijå±ŀæĿIJæĸĻ
    0.08
    Activations Density 0.011%

    No Known Activations