© 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. 41508
    Prev
    Next
    INDEX
    Explanations

    side by side, parallel, alongside

    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
    -0.09
    ÙħÙĨد
    -0.08
    mals
    -0.08
    骨åŃIJéĩĮ
    -0.08
    नà¥įदà¥įर
    -0.08
     latter
    -0.08
    kund
    -0.08
    HostException
    -0.08
    å¿ħåħĪ
    -0.08
    åħĭèIJ¨æĸ¯
    -0.08
    POSITIVE LOGITS
    -sama
    0.10
    并åĪĹ
    0.09
     nhau
    0.09
    ging
    0.07
     parallel
    0.07
    parallel
    0.07
    èĢĮåĿIJ
    0.07
    çĶŁè¾ī
    0.07
    Parallel
    0.07
    å¹³è¡Į
    0.07
    Activations Density 0.020%

    No Known Activations