© 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. 32946
    Prev
    Next
    INDEX
    Explanations

    critical point, temperature, scaling, current

    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
    å±ħæĺĵ
    -0.10
    å¾·åŁº
    -0.09
    chet
    -0.09
    ÙĨز
    -0.08
    ream
    -0.08
    lays
    -0.08
    åı¤å±ĭ
    -0.08
    otos
    -0.08
    ä½¼
    -0.08
    ussy
    -0.07
    POSITIVE LOGITS
    state
    0.08
    液æĢģ
    0.07
     state
    0.07
    ecker
    0.07
     states
    0.07
    液
    0.06
     gas
    0.06
    温度åĴĮ
    0.06
     Jab
    0.06
    fluid
    0.06
    Activations Density 0.002%

    No Known Activations