© 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. 18032
    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
    anel
    -0.07
     ...
    -0.07
    меÑĢа
    -0.07
    é³³
    -0.06
    alsa
    -0.06
    lings
    -0.06
    ×Ļ×Ķ
    -0.06
    cente
    -0.06
    éric
    -0.06
     ...\
    -0.06
    POSITIVE LOGITS
    åī¯ç§ĺ书éķ¿
    0.07
    ðŁĺī
    0.07
    impat
    0.07
    æĹıèĩªæ²»åĮº
    0.07
     KEP
    0.07
    bull
    0.06
    éĺ¿åħĭ
    0.06
    åĬłåħ¥æĶ¶èĹı
    0.06
    éĹ®é¢ĺçļĦèĥ½åĬĽ
    0.06
    ее
    0.06
    Activations Density 0.000%

    No Known Activations