© 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. 50378
    Prev
    Next
    INDEX
    Explanations

    guide, inform, help

    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
    acker
    -0.07
    磶
    -0.07
    æĿ¥å¾Ĺ
    -0.07
    åĵĪéĩĮ
    -0.07
    交代
    -0.06
    .reason
    -0.06
     kia
    -0.06
    ãĤ«ãĥ¼
    -0.06
    emar
    -0.06
    å¾Īä¸į
    -0.06
    POSITIVE LOGITS
    ä½ij
    0.08
    并å®ĮæĪIJ
    0.08
    ******/
    0.08
    åĪ°è´¦
    0.07
    å¿ĺæİī
    0.07
    orum
    0.07
    并讲è¯Ŀ
    0.07
    äºijå³°
    0.07
    æĥ®
    0.07
    /format
    0.07
    Activations Density 0.002%

    No Known Activations