© 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. 38689
    Prev
    Next
    INDEX
    Explanations

    etc

    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
     {//
    -0.08
    éĺ¿åħĭ
    -0.07
    arius
    -0.07
    -chain
    -0.07
    æī°
    -0.06
    æĵ¾
    -0.06
    诲
    -0.06
    خبار
    -0.06
    iste
    -0.06
    ariat
    -0.06
    POSITIVE LOGITS
    ä¿ĬæĿ°
    0.07
    天éªĦ
    0.07
    ray
    0.07
    åĪĨå·¦åı³
    0.07
    anye
    0.06
    anken
    0.06
    éģĵè¿ľ
    0.06
    owie
    0.06
    CJK
    0.06
    оÑģÑĤо
    0.06
    Activations Density 0.004%

    No Known Activations