© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14701
    Prev
    Next
    INDEX
    Explanations

    javascript, code, files

    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
    abat
    -0.07
    åĿŀ
    -0.06
    ä¸įçĿĢ
    -0.06
    acken
    -0.06
    iach
    -0.06
    ãĤĮãģŁãĤĬ
    -0.06
    ä¸Ģæĥ³åĪ°
    -0.06
    ente
    -0.06
    ´
    -0.06
    zysz
    -0.06
    POSITIVE LOGITS
    çļĦåħ¶ä»ĸ
    0.08
    è¿ĺ表示
    0.07
    shm
    0.07
     anyways
    0.07
    çļĦè¿Ļç§į
    0.07
     stessi
    0.07
     stesse
    0.07
    åı¦ä¸Ģç§į
    0.07
     ALSO
    0.07
    versi
    0.06
    Activations Density 0.644%

    No Known Activations