© 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. 1304
    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
    sworth
    -0.07
    tml
    -0.07
    tle
    -0.07
    wana
    -0.07
    еÑĪе
    -0.07
    ÑģÑĤв
    -0.06
    ITES
    -0.06
     withdrawn
    -0.06
    对è§Ĩ
    -0.06
    re
    -0.06
    POSITIVE LOGITS
    orden
    0.07
    avr
    0.07
    (_,
    0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.07
    erti
    0.07
    udz
    0.07
    chu
    0.07
    klı
    0.07
    è½½åħ¥
    0.07
    utas
    0.07
    Activations Density 0.000%

    No Known Activations