© 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. 27609
    Prev
    Next
    INDEX
    Explanations

    finite state

    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
    æł·çļĦ
    -0.08
    czy
    -0.08
    ä¾ĨçļĦ
    -0.08
    ηÏĥη
    -0.08
    ãĥ³ãĤ°
    -0.08
    iest
    -0.08
    ingle
    -0.08
    chend
    -0.07
    ä¸Ģ声
    -0.07
    bery
    -0.07
    POSITIVE LOGITS
    -ish
    0.11
    Ø©
    0.10
    esimal
    0.09
    /non
    0.08
    -dimensional
    0.08
     sayıda
    0.08
    å¸
    0.08
    -lived
    0.08
    iated
    0.08
    -scale
    0.08
    Activations Density 0.007%

    No Known Activations