© 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. 18460
    Prev
    Next
    INDEX
    Explanations

    fruits and vegetables

    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
    eworthy
    -0.08
    abouts
    -0.08
    er
    -0.08
    menti
    -0.08
     kest
    -0.07
     Affaires
    -0.07
    ertext
    -0.07
    çĹĩ
    -0.07
    filer
    -0.07
    adays
    -0.07
    POSITIVE LOGITS
    ually
    0.11
    UILD
    0.08
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.08
    icide
    0.08
    åIJįå±±
    0.08
    为主çļĦ
    0.07
    UNDLE
    0.07
    δÎŃ
    0.07
    lieb
    0.07
    iliary
    0.07
    Activations Density 0.021%

    No Known Activations