© 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. 44985
    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
    å¾Ĺèµ·
    -0.08
    缨
    -0.07
    ish
    -0.07
    æ¯ı天æĻļä¸Ĭ
    -0.07
    ieta
    -0.07
    atil
    -0.07
    HAM
    -0.07
    GAN
    -0.06
    æĬĬæĪij们
    -0.06
    achel
    -0.06
    POSITIVE LOGITS
    omatik
    0.07
    lineno
    0.06
    å·²ä¸İ
    0.06
    obil
    0.06
     Deliver
    0.06
    avig
    0.06
    _fmt
    0.06
    å«
    0.06
    ä½Ī
    0.06
    å¹³æĺĵ
    0.06
    Activations Density 0.000%

    No Known Activations