© 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. 18563
    Prev
    Next
    INDEX
    Explanations

    sections or topics

    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
    åİķ
    -0.08
    éĬŃ
    -0.08
    upun
    -0.08
    upert
    -0.08
    wijs
    -0.08
    æĮºèº«
    -0.08
    ª
    -0.07
    май
    -0.07
    ANTITY
    -0.07
    crast
    -0.07
    POSITIVE LOGITS
    alized
    0.07
    tid
    0.07
    obe
    0.07
    å°Ī
    0.07
    :
    0.06
    lad
    0.06
    åIJį为
    0.06
    orts
    0.06
     dedicated
    0.06
    ä¸ĵ
    0.06
    Activations Density 0.006%

    No Known Activations