© 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. 45980
    Prev
    Next
    INDEX
    Explanations

    Guys School

    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
    åħ¨åĽ½äººå¤§å¸¸å§Ķä¼ļ
    -0.08
     istrinya
    -0.08
     civilian
    -0.08
    åįĹä¸ĭ
    -0.07
    weep
    -0.07
    aguay
    -0.07
    ảo
    -0.07
    _LOOK
    -0.07
    ancier
    -0.07
    aurant
    -0.07
    POSITIVE LOGITS
    å·¥ç§ij
    0.08
    çĶ·æĸ¹
    0.07
    è¿ĺè´·
    0.07
    åIJij被åijĬ
    0.06
    wan
    0.06
    Ĥ
    0.06
    ula
    0.06
    ura
    0.06
    åĮĹæĸ¹
    0.06
    ÙĪاÙĨ
    0.06
    Activations Density 0.527%

    No Known Activations