© 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. 63104
    Prev
    Next
    INDEX
    Explanations

    writing and time

    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
    aze
    -0.07
    åºĦ
    -0.07
    idade
    -0.07
    loff
    -0.07
    yto
    -0.07
     Série
    -0.07
    izz
    -0.06
    æĶ¿æ²»å±Ģ
    -0.06
    ä¸ĢåĨį
    -0.06
    czyk
    -0.06
    POSITIVE LOGITS
    缪
    0.08
    å¾ĹæĪij
    0.07
    ngth
    0.07
    åħ³äºĨ
    0.07
    inion
    0.07
    خاÙĨÙĩ
    0.07
    ãĥ©ãĥ¼
    0.07
    clu
    0.07
    åħĭæĭī
    0.07
    å¦Ĥä½ķæīįèĥ½
    0.06
    Activations Density 0.001%

    No Known Activations