© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    setting variables with global or specific scope

    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
    olt
    -0.07
    pite
    -0.07
    åĩ°
    -0.07
    .ordinal
    -0.07
    hof
    -0.06
     tenden
    -0.06
    linger
    -0.06
    ä½ľä¸ºä¸Ģ家
    -0.06
    循
    -0.06
    ve
    -0.06
    POSITIVE LOGITS
    á»įt
    0.08
    issons
    0.08
     -.
    0.07
    çĹħ
    0.07
    ogr
    0.07
    allel
    0.07
    ksam
    0.07
     Gang
    0.07
    andum
    0.07
    isson
    0.07
    Activations Density 0.001%

    No Known Activations