© 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. 45194
    Prev
    Next
    INDEX
    Explanations

    javascript syntax

    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
    onaldo
    -0.08
     swept
    -0.07
    æľ¬è½®
    -0.07
    arpa
    -0.07
     Pickup
    -0.07
    ulin
    -0.07
    æĪijè¦ģæĬķè¯ī
    -0.06
    uffman
    -0.06
    /world
    -0.06
    .sap
    -0.06
    POSITIVE LOGITS
     syntax
    0.11
     workaround
    0.11
     `.
    0.09
    æŃ£ç¡®ä½¿çĶ¨
    0.09
     synt
    0.09
    解åĨ³æĸ¹æ¡Ī
    0.09
     funcional
    0.09
    è¯Ńæ³ķ
    0.08
     Syntax
    0.08
    Syntax
    0.08
    Activations Density 2.391%

    No Known Activations