© 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. 2138
    Prev
    Next
    INDEX
    Explanations

    metalloid and metal endings

    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
    vel
    -0.08
     tatt
    -0.07
    illé
    -0.07
    ayout
    -0.07
     fid
    -0.07
    éĿĴ天
    -0.07
    æ¸ł
    -0.06
    ADR
    -0.06
    è¡·
    -0.06
    å¥Ĺ
    -0.06
    POSITIVE LOGITS
    çķĮ线
    0.07
    shima
    0.07
    ä¾ĭå¤ĸ
    0.07
    -turned
    0.07
     excepción
    0.07
    åĤ¾åIJij
    0.07
    æ°§åĮĸçī©
    0.07
    éŨ类
    0.07
     Exceptions
    0.07
    meric
    0.07
    Activations Density 0.002%

    No Known Activations