© 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. 4106
    Prev
    Next
    INDEX
    Explanations

    0 or 1 following numbers

    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
    rav
    -0.08
    ↵
    -0.07
    ↵↵
    -0.07
    italia
    -0.06
    æĹ¥æĬ¥
    -0.06
    iro
    -0.06
    èĢĮæŃ»
    -0.06
    çĶŁæŃ»
    -0.06
    esser
    -0.06
    çļĦç»ĵåIJĪ
    -0.06
    POSITIVE LOGITS
    तिà¤ķ
    0.08
    upati
    0.08
    তিà¦ķ
    0.08
    ungsver
    0.08
    ymm
    0.08
    èĪĸ
    0.07
    åIJ¾å°Ķ
    0.07
    çıĪ
    0.07
    usche
    0.07
    {text
    0.07
    Activations Density 0.007%

    No Known Activations