© 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. 18196
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

    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
    .removeAttribute
    -0.09
    anty
    -0.08
    ogy
    -0.08
    uran
    -0.07
    éĹ®é¢ĺåĴĮ
    -0.07
    ç§ijæĬĢä¼ģä¸ļ
    -0.07
    åħ¶èº«
    -0.07
     rued
    -0.07
    åIJĦæĹı
    -0.07
    度åĴĮ
    -0.07
    POSITIVE LOGITS
    _ng
    0.07
    çĦ¶å¤§
    0.07
    ITLE
    0.07
    妻
    0.07
    adel
    0.07
    å¼łæĻĵ
    0.07
    _TRI
    0.06
    Ùģر
    0.06
    £o
    0.06
    flatten
    0.06
    Activations Density 0.178%

    No Known Activations