© 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. 8759
    Prev
    Next
    INDEX
    Explanations

    relation or comparison between items

    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
    erweise
    -0.10
    clearfix
    -0.08
    aic
    -0.08
    länd
    -0.08
    åĬ©äºİ
    -0.08
    ¹
    -0.08
    ï¾ŀ
    -0.08
    Ïįν
    -0.08
    enko
    -0.07
    ìį¨
    -0.07
    POSITIVE LOGITS
     ÙĪبÙĬÙĨ
    0.12
    Ø©
    0.10
    quiera
    0.09
    gether
    0.08
     Ñģобой
    0.08
    åľ°å¤´
    0.08
    /on
    0.08
    unload
    0.08
    ìĦľëĬĶ
    0.08
    /to
    0.08
    Activations Density 0.092%

    No Known Activations