© 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. 13897
    Prev
    Next
    INDEX
    Explanations

    Japanese series, song, career, history

    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
    ‘
    -0.07
     ‘
    -0.07
    ane
    -0.06
    âĢ¦âĢ¦
    -0.06
     âĢ¦
    -0.06
    pp
    -0.06
     Cupertino
    -0.06
    åĢĻ
    -0.06
     I
    -0.06
    âĢ¦
    -0.06
    POSITIVE LOGITS
    ezd
    0.09
    údo
    0.09
    Introduced
    0.09
    [src
    0.08
     Decompiled
    0.08
    .lu
    0.08
    lesa
    0.08
    أة
    0.08
    èrement
    0.08
     Ñģига
    0.08
    Activations Density 1.244%

    No Known Activations