© 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. 3204
    Prev
    Next
    INDEX
    Explanations

    urls starting with ://

    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
    å®ĺæĸ¹åįļ客
    -0.08
    elden
    -0.07
    umph
    -0.06
    umat
    -0.06
    尼奥
    -0.06
    æī©å±ķèµĦæĸĻ
    -0.06
    以ä¸Ĭå°±æĺ¯
    -0.06
    gara
    -0.06
    éĵ¶å±±
    -0.06
    nene
    -0.06
    POSITIVE LOGITS
    /repos
    0.08
    petto
    0.07
    rakt
    0.07
    訪
    0.07
    å¤įåĪ¶éĵ¾æİ¥
    0.07
    ocos
    0.07
    itionally
    0.07
    lieb
    0.07
    æĹ¥åĪ¶
    0.07
    artz
    0.07
    Activations Density 1.040%

    No Known Activations