© 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. 30416
    Prev
    Next
    INDEX
    Explanations

    code block endings

    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
    ness
    -0.09
    ation
    -0.09
    elly
    -0.08
    bing
    -0.07
    osti
    -0.07
    ales
    -0.07
    oles
    -0.07
    Ø©
    -0.07
    opez
    -0.07
     */,
    -0.07
    POSITIVE LOGITS
    <|box_end|>
    0.08
    ambu
    0.07
    jord
    0.07
    énk
    0.06
    xAB
    0.06
    verzeichnis
    0.06
    xBC
    0.06
    ликÑĤ
    0.06
    BuilderInterface
    0.06
     пеÑĢеме
    0.06
    Activations Density 0.095%

    No Known Activations