© 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. 21133
    Prev
    Next
    INDEX
    Explanations

    boolean true with symbols

    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
    ä¸Ńæĸĩç½ij
    -0.07
    dda
    -0.07
    åĴ«å°º
    -0.07
    eria
    -0.07
    Ñģок
    -0.07
    çīĪæĿĥå½Ĵ
    -0.06
    å¹³éĺ³
    -0.06
    ä¸ĢæĿ¡è¡Ĺ
    -0.06
    ignal
    -0.06
    issa
    -0.06
    POSITIVE LOGITS
    vester
    0.07
    kod
    0.07
    ä¸įå®ĮçļĦ
    0.07
    éĽ¨éľ²
    0.07
    esor
    0.07
    anky
    0.07
    ECTR
    0.07
    çĶ³è¯·åĬŀçIJĨ
    0.07
    éªĹ
    0.07
    uci
    0.06
    Activations Density 0.006%

    No Known Activations