© 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. 3122
    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
    اÙĨات
    -0.07
    æį®æѤ
    -0.07
    jo
    -0.07
    jh
    -0.07
    -0.07
    åħ¶ä¸ŃçļĦ
    -0.07
     counterparts
    -0.06
    onato
    -0.06
     additionally
    -0.06
     others
    -0.06
    POSITIVE LOGITS
    øb
    0.08
    ERO
    0.07
    LOTS
    0.07
    æĪĸåĪ©çĶ¨
    0.07
    agos
    0.07
     passo
    0.07
    ä¸ĢæľŁå·¥ç¨ĭ
    0.07
     ÙĪتخ
    0.07
    缮ä¸į
    0.07
    çĭ°
    0.06
    Activations Density 0.000%

    No Known Activations