© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 34341
    Prev
    Next
    INDEX
    Explanations

    compact sets

    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
    acers
    -0.10
     herald
    -0.08
    ế
    -0.08
    olet
    -0.08
    ä¸ĢåŃĹ
    -0.08
    赤åŃĹ
    -0.07
     tapped
    -0.07
     kancel
    -0.07
    ÙģÙĬÙģ
    -0.07
    acer
    -0.07
    POSITIVE LOGITS
     bounded
    0.09
     closed
    0.09
    å¯ĨéĹŃ
    0.08
    closed
    0.08
    éĹŃ
    0.08
    Closed
    0.08
     coerc
    0.07
    uable
    0.07
     tertutup
    0.07
    stuk
    0.07
    Activations Density 0.009%

    No Known Activations