© 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. 9063
    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
    æľºæ¢°åĮĸ
    -0.07
     Dude
    -0.07
    é¢ĨåħĪçļĦ
    -0.07
    éĿ¢çĽ®
    -0.06
     dude
    -0.06
    ziale
    -0.06
     Atta
    -0.06
    ipse
    -0.06
    hood
    -0.06
    animated
    -0.06
    POSITIVE LOGITS
    å°½èģĮ尽责
    0.09
    __:
    0.08
    stens
    0.08
    vester
    0.08
    ä¸īå²ģ
    0.08
     apologise
    0.07
    оÑģÑĥ
    0.07
    vh
    0.07
    Svc
    0.07
    ESTA
    0.07
    Activations Density 0.000%

    No Known Activations