© 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. 34125
    Prev
    Next
    INDEX
    Explanations

    code identifiers and data types

    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
     Aer
    -0.07
    éĩijåŁİ
    -0.07
    izr
    -0.07
    cial
    -0.07
    zé
    -0.07
    κι
    -0.07
    deo
    -0.06
    æĭĻ
    -0.06
    <|box_end|>
    -0.06
    zec
    -0.06
    POSITIVE LOGITS
    áīµ
    0.08
    XX
    0.07
    è¸ıä¸Ĭ
    0.07
    è¢ĭé¼ł
    0.07
     presumably
    0.07
    缸å¤ĦçļĦ
    0.07
    æķĻäºİ
    0.07
    æħİ
    0.07
    ìĿ´ë²Ħ
    0.06
    ä¸Ģåıij
    0.06
    Activations Density 0.018%

    No Known Activations