© 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. 15628
    Prev
    Next
    INDEX
    Explanations

    sec followed by hyphen

    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
    åĪ»
    -0.06
    \\
    -0.06
    esion
    -0.06
    ï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭï¼Ĭ
    -0.06
    ero
    -0.06
    ry
    -0.06
    \n
    -0.06
    ella
    -0.06
    <br
    -0.06
    esse
    -0.06
    POSITIVE LOGITS
    <|im_start|>
    0.08
    ikes
    0.07
    оÑĤÑĢе
    0.07
    æ¡ĪçļĦ
    0.07
    ommer
    0.07
    षà¥įà¤Ł
    0.07
     arrayWith
    0.07
     onload
    0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.07
    ilus
    0.07
    Activations Density 1.724%

    No Known Activations