© 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. 14504
    Prev
    Next
    INDEX
    Explanations

    HI antibodies

    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
    eneric
    -0.08
    ostar
    -0.07
    大åĬŁ
    -0.06
    ))-
    -0.06
    åĴĮå¸ĮæľĽ
    -0.06
    ottage
    -0.06
    ä¹ĭæķ°
    -0.06
    INN
    -0.06
    lific
    -0.06
    ">&#
    -0.06
    POSITIVE LOGITS
    گرد
    0.07
    зин
    0.07
    igos
    0.07
    稽
    0.07
    avier
    0.07
    ãĥĶãĥĥãĤ¯
    0.07
     Gim
    0.07
    ignan
    0.07
    ibur
    0.07
    ĥĿ
    0.07
    Activations Density 0.016%

    No Known Activations