© 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. 18774
    Prev
    Next
    INDEX
    Explanations

    beginning of quotes

    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
    æĺ¥åħī
    -0.07
    ote
    -0.07
    ãģĬãģĭ
    -0.07
     han
    -0.06
    response
    -0.06
    omed
    -0.06
    è¹
    -0.06
    ç¶ĵ
    -0.06
     response
    -0.06
    åĦŁ
    -0.06
    POSITIVE LOGITS
    ä½ľå¼Ĭ
    0.08
    ίδα
    0.08
    atu
    0.07
    ),"
    0.07
    ullet
    0.07
     Weed
    0.07
    gtest
    0.06
    /cs
    0.06
     mess
    0.06
    iche
    0.06
    Activations Density 0.183%

    No Known Activations