© 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. 48144
    Prev
    Next
    INDEX
    Explanations

    diagonal entries, self loops, axial beam

    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
    าà¸Ĺ
    -0.08
    raw
    -0.07
    Ãło
    -0.07
    utusan
    -0.07
    adm
    -0.06
    èļĬ
    -0.06
    cloud
    -0.06
    èļĬèĻ«
    -0.06
    fans
    -0.06
    ä¸¤äººåľ¨
    -0.06
    POSITIVE LOGITS
    à¤ķर
    0.08
    º¼
    0.07
    .diag
    0.07
    +self
    0.07
    åĴĮéĿŀ
    0.07
    mtx
    0.07
    emel
    0.07
    _diag
    0.07
    èĻ¹
    0.07
    ä¸İéĿŀ
    0.07
    Activations Density 0.003%

    No Known Activations