© 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. 47526
    Prev
    Next
    INDEX
    Explanations

    Sin City Presents

    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
    INGER
    -0.07
    ersive
    -0.07
    -0.07
    oken
    -0.07
     eign
    -0.07
     겸
    -0.07
    å®īè¾¾
    -0.07
    usak
    -0.07
    понен
    -0.06
    OKEN
    -0.06
    POSITIVE LOGITS
    ever
    0.07
    sic
    0.07
    кÑĸн
    0.07
    ams
    0.06
    æľ¬èº«
    0.06
    aison
    0.06
    acy
    0.06
    arks
    0.06
    æł¸å¿ĥçļĦ
    0.06
    ly
    0.06
    Activations Density 0.140%

    No Known Activations