© 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. 32685
    Prev
    Next
    INDEX
    Explanations

    FULLNAME or NAME

    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
    缸è¾ħ缸æĪIJ
    -0.08
    son
    -0.08
    almente
    -0.08
    èħ¾èħ¾
    -0.08
    اØŃت
    -0.08
    endale
    -0.08
    a
    -0.08
    ened
    -0.07
    ìļĶ
    -0.07
    nar
    -0.07
    POSITIVE LOGITS
    ffect
    0.08
    èµŀè¿ĩ
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    lect
    0.08
    yclopedia
    0.08
    leanup
    0.08
    ลฯ
    0.08
    å®ĥ为
    0.08
    ytics
    0.07
    ÑģÑı
    0.07
    Activations Density 0.002%

    No Known Activations