© 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. 64383
    Prev
    Next
    INDEX
    Explanations

    minor and its common followers

    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
    aub
    -0.12
    Ø©
    -0.11
    entication
    -0.10
    oenix
    -0.10
    缸è¾ħ缸æĪIJ
    -0.09
    мп
    -0.09
    ações
    -0.09
    élia
    -0.08
    infeld
    -0.08
    earn
    -0.08
    POSITIVE LOGITS
    theless
    0.08
    ellaneous
    0.08
    ãģªãģĮãĤī
    0.08
    itized
    0.07
    Į
    0.07
    ities
    0.07
    apolis
    0.07
    ë§IJë¡ľ
    0.07
    ÑİÑģÑĮ
    0.07
    -league
    0.07
    Activations Density 0.023%

    No Known Activations