© 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. 46649
    Prev
    Next
    INDEX
    Explanations

    roles and their subsequent actions

    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
     our
    -0.08
    å®ĥ们çļĦ
    -0.08
    å½ĵæĪij们
    -0.08
     their
    -0.08
     nhau
    -0.07
     ë¶Ī구íķĺê³ł
    -0.07
    å®ĥéĤ£
    -0.07
    à¸ŀวà¸ģ
    -0.07
    ä½Ĩæĺ¯æĪij们
    -0.07
    æĪij们çļĦå·¥ä½ľ
    -0.07
    POSITIVE LOGITS
    (s
    0.10
    's
    0.09
    cule
    0.09
    cules
    0.09
    aviest
    0.08
    æľ¬äºº
    0.08
    /operator
    0.07
    `s
    0.07
    angan
    0.07
    (es
    0.07
    Activations Density 0.086%

    No Known Activations