© 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. 56401
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    eness
    -0.09
    acle
    -0.07
     (âĢŀ
    -0.07
    isted
    -0.07
     frustra
    -0.07
    arze
    -0.07
    enes
    -0.06
    orary
    -0.06
    veau
    -0.06
    iveness
    -0.06
    POSITIVE LOGITS
    amai
    0.07
     lao
    0.07
    åĬŁ
    0.06
    intptr
    0.06
    çĶ£
    0.06
    enton
    0.06
    åįģåħ¨
    0.06
     globally
    0.06
     reg
    0.06
    èŀĤ
    0.06
    Activations Density 0.424%

    No Known Activations