© 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. 23635
    Prev
    Next
    INDEX
    Explanations

    equation components

    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
    çĤľ
    -0.07
    åĬ´
    -0.07
    èĢIJåĬ³
    -0.07
    _ALIGN
    -0.06
    并举
    -0.06
    বà§ĩ
    -0.06
    å¨ľ
    -0.06
     stan
    -0.06
    娲
    -0.06
    lement
    -0.06
    POSITIVE LOGITS
    riel
    0.10
     Mellon
    0.08
    ØŃÙĬÙĨ
    0.07
    åĴĮåIJĮäºĭ
    0.07
    è¥¿åŁŁ
    0.07
    itzer
    0.07
    ÑĢани
    0.07
    itse
    0.07
    arking
    0.06
    Isl
    0.06
    Activations Density 0.002%

    No Known Activations