© 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. 21249
    Prev
    Next
    INDEX
    Explanations

    second to trauma

    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
    iglio
    -0.07
    墨å°Ķ
    -0.07
    è§ģ人
    -0.07
    enaar
    -0.07
    än
    -0.07
    æı
    -0.07
    åıªè¦ģä¸Ģ
    -0.07
    ä¸İåħ¶
    -0.07
    üng
    -0.07
     slightest
    -0.07
    POSITIVE LOGITS
    并åĪĹ
    0.10
     another
    0.08
     Parad
    0.08
    çļĦåı¦ä¸Ģ
    0.07
     parallel
    0.07
    åIJĮ为
    0.07
    ongs
    0.07
    并称
    0.07
     alternative
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    Activations Density 0.242%

    No Known Activations