© 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. 43915
    Prev
    Next
    INDEX
    Explanations

    special characters followed by numbers or words

    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
    åıĬæŶæİĮæı¡
    -0.09
    еÑģÑĤа
    -0.08
    åĨ²åĬ¨
    -0.08
    欢è¿İåħ³æ³¨
    -0.08
    <meta
    -0.08
    .tw
    -0.08
    ä»ħä»£è¡¨ä½ľèĢħ
    -0.08
    asiun
    -0.08
    æĸ°ç¤¾
    -0.08
    :title
    -0.08
    POSITIVE LOGITS
    è¤Ĥ
    0.06
    åĪĨ
    0.06
    ud
    0.06
    âteau
    0.06
    \
    0.06
    elaar
    0.06
     تاک
    0.06
    ynchronous
    0.06
    å±Ĥ次
    0.06
    CTL
    0.05
    Activations Density 0.004%

    No Known Activations