© 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. 9998
    Prev
    Next
    INDEX
    Explanations

    real estate and product descriptions

    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
    .className
    -0.07
    èĩªçĦ¶ä¼ļ
    -0.07
     circumstance
    -0.07
    顶
    -0.07
    åĽłä¸ºæľīäºĨ
    -0.07
    ommen
    -0.07
    éļı
    -0.07
    icot
    -0.07
    éĻħ
    -0.06
    æĹłè·¯
    -0.06
    POSITIVE LOGITS
    uÅŁtur
    0.08
    stands
    0.07
     Hoy
    0.07
    cket
    0.07
    ðŁĺī
    0.07
    BCM
    0.07
    chio
    0.07
    ######
    0.07
    emberg
    0.06
    shire
    0.06
    Activations Density 0.001%

    No Known Activations