© 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. 40372
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide or messenger RNA

    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
    isse
    -0.07
    /cop
    -0.07
    sdale
    -0.07
    teria
    -0.06
    ceo
    -0.06
     ded
    -0.06
    çĮľçĮľ
    -0.06
    emaker
    -0.06
    artes
    -0.06
    达产年
    -0.06
    POSITIVE LOGITS
    ç®Ģ称
    0.08
    dit
    0.08
    (CG
    0.07
    ÄĽn
    0.07
    onium
    0.07
    (V
    0.07
    adium
    0.07
    éľ¹éĽ³
    0.07
    ags
    0.07
    (H
    0.07
    Activations Density 1.708%

    No Known Activations