© 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. 65308
    Prev
    Next
    INDEX
    Explanations

    listing features or services

    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
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.08
    æľī以ä¸ĭ
    -0.07
    és
    -0.06
     bom
    -0.06
    **
    -0.06
    nat
    -0.06
    ies
    -0.06
    è¨Ģä¹ĭ
    -0.06
    溢
    -0.06
    nia
    -0.06
    POSITIVE LOGITS
    celet
    0.08
    æķħèĢĮ
    0.07
    媲
    0.07
    èī²åĪĹ
    0.07
    ille
    0.07
    å¦ĤèĬ±
    0.07
    件å¥Ĺ
    0.07
    hton
    0.07
    çĻ½éľ²
    0.07
    ä¼ģä¸ļæıIJä¾Ľ
    0.07
    Activations Density 0.016%

    No Known Activations