© 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. 30004
    Prev
    Next
    INDEX
    Explanations

    compound mathematical operations

    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
    ì°°
    -0.08
    åıĬåħ¶åºĶçĶ¨
    -0.07
    绣
    -0.06
    çŀİ
    -0.06
     alternate
    -0.06
    uni
    -0.06
    orre
    -0.06
    åīįä¸ī
    -0.06
     warrants
    -0.06
    rain
    -0.06
    POSITIVE LOGITS
     afterwards
    0.08
    åIJİè¦ģ
    0.08
    hape
    0.08
     afterward
    0.08
    gether
    0.08
     ÑģвеÑĢÑħÑĥ
    0.07
    -dir
    0.07
    æīĢ以è¦ģ
    0.07
    è¡Ģä¸Ŀ
    0.07
    yper
    0.07
    Activations Density 0.004%

    No Known Activations