© 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. 40841
    Prev
    Next
    INDEX
    Explanations

    second error

    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
    opsis
    -0.06
    iken
    -0.06
    uton
    -0.06
    åħ¶äºĭ
    -0.06
     port
    -0.06
     funnel
    -0.06
    éĩijåŁİ
    -0.06
    iets
    -0.06
    tte
    -0.06
    ight
    -0.06
    POSITIVE LOGITS
    orz
    0.08
    ForKey
    0.08
    .slim
    0.08
    ä¸ĢèĪ¬èĢĮè¨Ģ
    0.07
     Gow
    0.07
    ä¸ĢèĪ¬æĿ¥è¯´
    0.07
    ritz
    0.07
    huri
    0.07
    .sy
    0.07
    罡
    0.07
    Activations Density 0.006%

    No Known Activations