© 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. 55517
    Prev
    Next
    INDEX
    Explanations

    compilation of legislation

    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
    è¦ģæ±Ĥ
    -0.08
    enza
    -0.07
     mur
    -0.07
    all
    -0.07
    èĨ½
    -0.07
    alli
    -0.06
    urf
    -0.06
    å®Ļ
    -0.06
    gut
    -0.06
    è´¨
    -0.06
    POSITIVE LOGITS
    वार
    0.09
    æĪIJåĬŁåIJİåį³åı¯
    0.08
    ä¸İå®ŀéĻħ
    0.08
    berge
    0.08
    罩
    0.08
    .gradle
    0.07
    eor
    0.07
    adamente
    0.07
    .Model
    0.07
    вига
    0.07
    Activations Density 0.003%

    No Known Activations