© 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. 44120
    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
    еÑĢÑĭ
    -0.06
    æĭ¼
    -0.06
    èĦ¯
    -0.06
    igin
    -0.06
    ây
    -0.06
    éļı便
    -0.06
    _each
    -0.06
    è°ģ
    -0.06
    ype
    -0.06
    entic
    -0.06
    POSITIVE LOGITS
    æ³Ĭ
    0.08
    å¾ľå¾ī
    0.08
    ScrollIndicator
    0.07
    ç§Ģ丽
    0.07
    combe
    0.07
    ITIONS
    0.07
    POST
    0.07
    è¿ĺ对
    0.07
    ÐĽÐ¸
    0.06
    hov
    0.06
    Activations Density 0.000%

    No Known Activations