© 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. 20697
    Prev
    Next
    INDEX
    Explanations

    Law, resolution, or act numbers

    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
    pitch
    -0.08
    æĽ´å¤ļèµĦ讯
    -0.08
    ehn
    -0.08
     pitch
    -0.08
    spill
    -0.08
    åħ¶å®ĥåªĴä½ĵ
    -0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.08
     Tengah
    -0.07
    ATEG
    -0.07
    AUSE
    -0.07
    POSITIVE LOGITS
    åı·
    0.07
    åı·åĴĮ
    0.07
    èĻŁ
    0.07
    åı·çļĦ
    0.07
    0.06
     hard
    0.06
     annex
    0.06
    Âł
    0.06
     (
    0.06
    åĮĹé£İ
    0.06
    Activations Density 0.201%

    No Known Activations