© 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. 28462
    Prev
    Next
    INDEX
    Explanations

    alone or singular choice

    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
    èche
    -0.08
    apel
    -0.07
    odies
    -0.07
    æĥ®
    -0.07
    ç½Ĺå¾·
    -0.07
    -fast
    -0.07
    _requested
    -0.07
    -env
    -0.07
    odi
    -0.07
    uning
    -0.07
    POSITIVE LOGITS
     Alone
    0.12
    åįķçĭ¬çļĦ
    0.12
    åįķçĭ¬
    0.12
     alone
    0.11
    -alone
    0.10
    åĸ®çį¨
    0.10
     sozinho
    0.09
    alone
    0.09
    ioc
    0.08
     without
    0.08
    Activations Density 0.072%

    No Known Activations