© 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. 56367
    Prev
    Next
    INDEX
    Explanations

    linear coding

    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
    avat
    -0.06
    eps
    -0.06
    lisi
    -0.06
     NOW
    -0.06
     неоÑĤ
    -0.06
    etro
    -0.06
    汶
    -0.06
    ä»ij
    -0.06
    ä¸Ģ次åıĪä¸Ģ次
    -0.06
    æĺ¯éĿŀ
    -0.06
    POSITIVE LOGITS
    å¿ħ须符åIJĪ
    0.07
    è¯ķçĿĢ
    0.07
    chting
    0.07
    cona
    0.07
     sprawdz
    0.07
     simpler
    0.07
    åı¯ä»¥æ»¡è¶³
    0.07
    _checked
    0.07
    enius
    0.07
    éļĻ
    0.07
    Activations Density 0.002%

    No Known Activations