© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42513
    Prev
    Next
    INDEX
    Explanations

    trivial, non-trivial

    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
    vog
    -0.07
    ovac
    -0.07
    ocr
    -0.07
    áŀİ
    -0.07
    /IP
    -0.07
    otron
    -0.07
    orgh
    -0.07
    ìłł
    -0.07
    arer
    -0.06
    Ïħνα
    -0.06
    POSITIVE LOGITS
    ivial
    0.09
    ç»ħ
    0.07
    edly
    0.07
     (>
    0.07
    ithub
    0.07
    .promise
    0.07
    俨
    0.07
    /full
    0.07
    以太
    0.07
    æ¼¾
    0.07
    Activations Density 0.004%

    No Known Activations