© 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. 55855
    Prev
    Next
    INDEX
    Explanations

    graphene, platform, kayak, store, Warcraft

    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
    ernel
    -0.07
    kontak
    -0.07
     Tisch
    -0.07
    ritz
    -0.07
    è¦ģä¹Ī
    -0.07
    oney
    -0.07
    FFE
    -0.06
    sterol
    -0.06
    è¿Ļä¸ªä¸ľè¥¿
    -0.06
     Inv
    -0.06
    POSITIVE LOGITS
    以å¤ĸçļĦ
    0.08
     without
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    ä¹ĭå¤ĸçļĦ
    0.07
    èĢĮåıĪ
    0.07
    åIJİåıĪ
    0.07
    åĬłæĭī
    0.07
    ä¸Ń带
    0.07
     ohne
    0.07
    ä½Ĩè¦ģ
    0.07
    Activations Density 0.054%

    No Known Activations