© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    parabolic / parabel compounds

    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
    OrCreate
    -0.11
    ivo
    -0.08
    دÙī
    -0.08
    俱ä¹IJéĥ¨
    -0.08
     berdua
    -0.07
    inkel
    -0.07
    borne
    -0.07
    å·´å°Ķ
    -0.07
    erval
    -0.07
    /disable
    -0.07
    POSITIVE LOGITS
    å½¢çļĦ
    0.09
    vorm
    0.08
    -eslint
    0.08
    oidal
    0.08
    abolic
    0.08
    mallow
    0.08
    ://{
    0.07
    usercontent
    0.07
    ://%
    0.07
    -like
    0.07
    Activations Density 0.002%

    No Known Activations