© 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. 12176
    Prev
    Next
    INDEX
    Explanations

    Event and fictional concepts

    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
    chg
    -0.07
    å¿Ĺæĺİ
    -0.07
    ä¸Ģ亮
    -0.07
    erty
    -0.07
    Unhandled
    -0.06
    Attempt
    -0.06
    resse
    -0.06
    ALAR
    -0.06
     Volk
    -0.06
    åĬłè½½æĽ´å¤ļ
    -0.06
    POSITIVE LOGITS
     hypothetical
    0.09
    åľ¨å®ŀéĻħ
    0.08
    idia
    0.08
    设æĥ³
    0.08
    å®ŀéĻħæĵįä½ľ
    0.08
    çĻ¾éĩĮ
    0.08
     imagined
    0.08
     fictional
    0.08
    æĭŁ
    0.08
    èĿī
    0.08
    Activations Density 0.268%

    No Known Activations