© 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. 18026
    Prev
    Next
    INDEX
    Explanations

    back, first, composed

    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
    æĸ°åĬłåĿ¡
    -0.08
    drag
    -0.08
    .force
    -0.07
    irk
    -0.07
    /misc
    -0.07
    qua
    -0.07
    leigh
    -0.07
    æ°¸ä¸į
    -0.07
     Sweep
    -0.07
    çī¹éķ¿çĶŁ
    -0.07
    POSITIVE LOGITS
     decrease
    0.08
    modifiable
    0.08
    æľīä½Ļ
    0.07
    æĹłåīį
    0.07
    åİļ
    0.07
    åı¯ä»¥åĨį
    0.07
    Exist
    0.07
    åĩı
    0.07
    å¾Ģåīį
    0.07
    Decre
    0.07
    Activations Density 0.060%

    No Known Activations