© 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. 40843
    Prev
    Next
    INDEX
    Explanations

    port state service

    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
    Unchecked
    -0.09
    usel
    -0.08
    ijski
    -0.08
     nimic
    -0.08
    еÑĢб
    -0.08
    :Event
    -0.08
    colas
    -0.08
    çİ¥
    -0.08
    å¸Ĥæĸ°
    -0.07
     estima
    -0.07
    POSITIVE LOGITS
    ate
    0.08
    adx
    0.07
     -
    0.06
    ÙİØ°
    0.06
    ob
    0.06
    Fs
    0.06
    ugu
    0.06
    æĺ¯åIJ¦åħ·æľī
    0.06
    rop
    0.06
    èĤ¯å®ļçļĦ
    0.06
    Activations Density 0.001%

    No Known Activations