© 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. 19291
    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
    TP
    -0.08
    tp
    -0.07
    æľīæĦı
    -0.07
    acs
    -0.07
    est
    -0.06
    缴æİ¥æĪĸ
    -0.06
    æĪijèĩªå·±çļĦ
    -0.06
    ing
    -0.06
    neo
    -0.06
     taman
    -0.06
    POSITIVE LOGITS
    ope
    0.08
    avs
    0.07
    ãĥīãĤŃ
    0.07
    çĨĬçĨĬ
    0.07
    HashCode
    0.07
    adini
    0.07
    Opcode
    0.07
     Dickinson
    0.07
    aving
    0.07
    atives
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.