© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2334
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Darling
    -0.08
    åħ°çī¹
    -0.07
    itung
    -0.07
    ål
    -0.07
    åħ¶çī¹å¾ģ
    -0.07
    æĪĸ缺
    -0.07
    ä¼ģä¸ļåIJįå½ķ
    -0.07
    ISIBLE
    -0.07
    phin
    -0.07
     appropriated
    -0.07
    POSITIVE LOGITS
    umas
    0.08
    avance
    0.07
    inken
    0.07
    urette
    0.07
    _ios
    0.07
    è´©
    0.07
    (END
    0.07
     versp
    0.07
    WithContext
    0.07
    utzt
    0.06
    Activations Density 0.000%

    No Known Activations