© 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. 64832
    Prev
    Next
    INDEX
    Explanations

    version number

    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
    łĢ
    -0.07
    .ascii
    -0.07
    åĴĮæĶ¹è¿Ľ
    -0.07
    ×ŀף
    -0.07
    edList
    -0.07
    æīĭä¸ĭ
    -0.07
    .azure
    -0.07
    è¦ģæĬĬ
    -0.07
    èĥ§
    -0.07
    åĬ¨åijĺ
    -0.07
    POSITIVE LOGITS
    uks
    0.08
    件å¥Ĺ
    0.08
    nage
    0.07
    æĪijæ°¸è¿ľ
    0.07
    chino
    0.07
    zew
    0.06
    chwitz
    0.06
    çĤ¹æѤ
    0.06
    jep
    0.06
    osate
    0.06
    Activations Density 0.008%

    No Known Activations