© 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. 27849
    Prev
    Next
    INDEX
    Explanations

    code snippet delimiters

    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
    \\\\
    -0.07
    able
    -0.07
     ob
    -0.07
    erno
    -0.07
    èĢĮè¿Ļç§į
    -0.06
    aat
    -0.06
    梦è§ģ
    -0.06
    åĨħ容åĮħæĭ¬
    -0.06
    åĵī
    -0.06
    o
    -0.06
    POSITIVE LOGITS
    ettings
    0.09
    _TODO
    0.08
    AuthService
    0.08
    Ä°Z
    0.07
    ied
    0.07
    å©ķ
    0.07
    essous
    0.07
     intelek
    0.07
    oui
    0.07
    ijnen
    0.07
    Activations Density 0.104%

    No Known Activations