© 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. 9022
    Prev
    Next
    INDEX
    Explanations

    either version

    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
    edly
    -0.09
    ulg
    -0.08
    κα
    -0.08
    Ö¼
    -0.08
    缸åħ³æ³ķå¾ĭ责任
    -0.08
    åį³ä½¿åľ¨
    -0.08
    ëģĶ
    -0.08
    esor
    -0.08
    ys
    -0.07
    manship
    -0.07
    POSITIVE LOGITS
    theless
    0.10
    ment
    0.10
    ments
    0.09
    rette
    0.07
    rett
    0.07
    mente
    0.07
    er
    0.07
    eru
    0.07
    odox
    0.07
    maal
    0.07
    Activations Density 0.030%

    No Known Activations