© 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. 4173
    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
    kees
    -0.10
    óf
    -0.09
    agak
    -0.08
    æv
    -0.08
    irts
    -0.08
    æ
    -0.08
    ezi
    -0.08
    atable
    -0.08
    trz
    -0.08
    onest
    -0.08
    POSITIVE LOGITS
     pre
    0.07
    lava
    0.06
    ç²
    0.06
     eg
    0.06
    天宫
    0.06
     accompanying
    0.06
    è¡¡
    0.06
     put
    0.06
    没æľī被
    0.06
     ex
    0.06
    Activations Density 0.000%

    No Known Activations