© 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. 15641
    Prev
    Next
    INDEX
    Explanations

    Fourth Court

    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
    ire
    -0.07
     pire
    -0.06
     darn
    -0.06
    yro
    -0.06
     dere
    -0.06
    son
    -0.06
    Eb
    -0.06
    yg
    -0.06
    IRE
    -0.06
    æ³ķæĺ¯
    -0.06
    POSITIVE LOGITS
    ikle
    0.08
    iteDatabase
    0.08
    liance
    0.08
    åĸĶ
    0.08
     menyar
    0.07
    rear
    0.07
    roupon
    0.07
    rero
    0.07
     pornstar
    0.07
    åĬłè½½æĽ´å¤ļ
    0.07
    Activations Density 0.001%

    No Known Activations