© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12548
    Prev
    Next
    INDEX
    Explanations

    database identifiers

    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
    rot
    -0.06
     op
    -0.06
    croft
    -0.05
     ID
    -0.05
     ad
    -0.05
    hart
    -0.05
    ax
    -0.05
     E
    -0.05
    v
    -0.05
    POSITIVE LOGITS
    masin
    0.09
    ãģıãĤĬ
    0.09
    essor
    0.09
    å¾ī
    0.09
    ÙĪÙĦÙĪج
    0.09
    اجة
    0.09
    ÙĨدر
    0.09
    éken
    0.08
    .jquery
    0.08
    Ế
    0.08
    Activations Density 0.025%

    No Known Activations