© 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. 45270
    Prev
    Next
    INDEX
    Explanations

    open subsets or neighborhoods

    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
    å¿«äºĨ
    -0.09
    å¿«åĪ°
    -0.08
    enate
    -0.07
    leur
    -0.07
    oning
    -0.07
    emel
    -0.07
    ering
    -0.07
    isten
    -0.07
    اتÙĬ
    -0.07
    å·´åħĭ
    -0.07
    POSITIVE LOGITS
    ness
    0.08
    /
    0.08
    -looking
    0.07
    vpn
    0.07
    ly
    0.07
    ä¸Ķåľ¨
    0.07
    incerely
    0.06
    ä¸Ķ
    0.06
    lude
    0.06
     athe
    0.06
    Activations Density 0.009%

    No Known Activations