© 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. 7862
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
    åħ¬èĭ±
    -0.06
    à¸Ħะ
    -0.06
     ÙĪÙĩÙĥذا
    -0.06
    Ø®ÙĨ
    -0.06
    à¸ļ
    -0.06
    ÑģоÑĢ
    -0.06
    engk
    -0.06
     Mec
    -0.05
     '::
    -0.05
    rières
    -0.05
    POSITIVE LOGITS
    ieger
    0.08
    hind
    0.08
    _DEFINITION
    0.07
    baus
    0.07
    andest
    0.07
    villa
    0.07
    loh
    0.07
     laku
    0.07
    afil
    0.07
    croft
    0.07
    Activations Density 0.057%

    No Known Activations