© 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. 10178
    Prev
    Next
    INDEX
    Explanations

    Oregon

    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
    ÅĽle
    -0.07
     INCIDENTAL
    -0.07
     drafts
    -0.07
    /welcome
    -0.07
     setHidden
    -0.07
     certif
    -0.07
     uncert
    -0.07
    ?>
    -0.06
    æĹłæĦ§
    -0.06
     PropertyValue
    -0.06
    POSITIVE LOGITS
    ugen
    0.06
    бий
    0.06
    stad
    0.06
    æ°¸è¿ľçļĦ
    0.06
    UG
    0.06
    anko
    0.06
    anu
    0.06
    pressa
    0.06
    ç¶
    0.06
    chting
    0.06
    Activations Density 0.425%

    No Known Activations