© 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. 62695
    Prev
    Next
    INDEX
    Explanations

    numbers and alphanumeric sequences

    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
    hal
    -0.07
    åĨįä¸Ĭæĸ°åı°éĺ¶
    -0.07
    ör
    -0.07
    OS
    -0.06
    IT
    -0.06
    ushi
    -0.06
    viz
    -0.06
    å©·
    -0.06
     Almighty
    -0.06
    bat
    -0.06
    POSITIVE LOGITS
    ÛĮتÛĮ
    0.09
    ä¸įçĶŁ
    0.08
    å¦ĤæѤçļĦ
    0.08
    eih
    0.07
    åħĭçļĦ
    0.07
    ansch
    0.07
    æĹłå¼Ĥ
    0.07
    vider
    0.07
    borg
    0.07
    å°Ķåħĭ
    0.07
    Activations Density 0.033%

    No Known Activations