© 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. 3960
    Prev
    Next
    INDEX
    Explanations

    IndexPath

    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
    ÙĤرة
    -0.07
    ãģ
    -0.07
    ä¸ĭè§Ĵ
    -0.07
     haz
    -0.07
    åł¡
    -0.06
    ued
    -0.06
    ISON
    -0.06
    ison
    -0.06
     sw
    -0.06
     Cung
    -0.06
    POSITIVE LOGITS
    è±ļ
    0.08
    erven
    0.08
    å¸ĸ
    0.08
    clam
    0.07
    anz
    0.07
    ohen
    0.07
    æľ¬é¢ĺ
    0.07
     kilom
    0.07
    -party
    0.07
    umi
    0.07
    Activations Density 0.021%

    No Known Activations