© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7955
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    缸çľĭ
    -0.08
    ousse
    -0.08
    åĶ¾
    -0.08
     prel
    -0.07
    aldi
    -0.07
    ovit
    -0.07
    æľĪçĶŁ
    -0.07
    ëĿ½
    -0.07
    ç½Ĺæ±ī
    -0.07
     cleaned
    -0.07
    POSITIVE LOGITS
    表彰
    0.08
    zech
    0.07
     Bir
    0.07
    emen
    0.07
    åij½åIJį为
    0.07
     Nobel
    0.07
     Äijo
    0.07
     derives
    0.06
    æ´½
    0.06
    çļĦåĽ½éĻħ
    0.06
    Activations Density 0.004%

    No Known Activations