© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62005
    Prev
    Next
    INDEX
    Explanations

    SIZES XL S 7 Y G WHAT

    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
    -0.09
    ¶
    -0.07
    -0.06
    é©°åIJį
    -0.06
    quette
    -0.06
    å¤Ħ女
    -0.06
    è¾ij
    -0.06
    æĹłå¿Į
    -0.06
    enne
    -0.06
    -0.06
    POSITIVE LOGITS
    æĤ¨åı¯èĥ½
    0.11
    俱ä¹IJéĥ¨
    0.10
    缸è¾ħ缸æĪIJ
    0.08
    othe
    0.08
    osso
    0.08
    åIJĮä¸Ĭ
    0.08
    mith
    0.08
    ocaly
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    ιαί
    0.07
    Activations Density 0.400%

    No Known Activations