© 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. 1402
    Prev
    Next
    INDEX
    Explanations

    setup distance positions

    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
    onds
    -0.08
    wald
    -0.07
    çķĻæģĭ
    -0.07
    åºĵéĩĮ
    -0.07
    å°ıé¢ĺ
    -0.07
    äºİä¸Ģ身
    -0.07
    æĴķè£Ĥ
    -0.07
    quette
    -0.07
    åĮºåĪ«äºİ
    -0.07
    _cf
    -0.07
    POSITIVE LOGITS
     setup
    0.11
     setups
    0.10
    æijĨæĶ¾
    0.09
    /setup
    0.09
     distance
    0.09
     ustaw
    0.09
    setup
    0.09
     SETUP
    0.08
    æĶ¾ç½®
    0.08
    Setup
    0.08
    Activations Density 0.008%

    No Known Activations