© 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. 2861
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    ãĥĪãĥª
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ory
    -0.07
     Cire
    -0.06
    ernal
    -0.06
    好åIJ§
    -0.06
    chado
    -0.06
    []>
    -0.06
    ode
    -0.06
    .today
    -0.06
    POSITIVE LOGITS
    ãĤ¥
    0.07
    ASIL
    0.07
    зÑĮ
    0.07
    nolo
    0.07
    orses
    0.07
    berger
    0.07
    æĦıè§ģåıįé¦Ī
    0.07
    Ĥ¬
    0.07
    溫åĴĮ
    0.07
     actionTypes
    0.06
    Activations Density 0.053%

    No Known Activations