© 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. 962
    Prev
    Next
    INDEX
    Explanations

    edges with weight or property conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    æIJħ
    -0.07
    æ¯Ķä¾ĭ为
    -0.07
    iete
    -0.07
     оÑĩа
    -0.07
    Globals
    -0.07
    带åĬ¨ä¸ĭ
    -0.06
    hcp
    -0.06
     toc
    -0.06
     McM
    -0.06
    active
    -0.06
    POSITIVE LOGITS
     weight
    0.08
    iless
    0.08
    路段
    0.08
     negotiated
    0.07
    æľºçĶµè®¾å¤ĩ
    0.07
    _weight
    0.07
    .Spring
    0.07
    มิ
    0.07
    婪
    0.07
    éģĩ
    0.07
    Activations Density 0.014%

    No Known Activations