© 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. 20539
    Prev
    Next
    INDEX
    Explanations

    mathematical and calendar events

    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
    ÙĬاÙĨ
    -0.07
    /usr
    -0.07
    ponder
    -0.07
    OMPI
    -0.07
    amber
    -0.06
    .overlay
    -0.06
    gian
    -0.06
    å¤įåį°
    -0.06
     Simpl
    -0.06
    enschaft
    -0.06
    POSITIVE LOGITS
    grab
    0.08
    åĽłåľ°
    0.08
    ä½
    0.08
    lett
    0.08
     uniformly
    0.07
    ä¸į欲
    0.07
    æĽĻ
    0.07
    áĥĹ
    0.07
    è¶ĬæĿ¥è¶Ĭå°ij
    0.07
    isans
    0.07
    Activations Density 0.005%

    No Known Activations