© 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. 21890
    Prev
    Next
    INDEX
    Explanations

    case separators

    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
    åħ¬åħ±é¢Ħç®Ĺ
    -0.07
    emis
    -0.07
    baum
    -0.07
    áĥĵáĥĶ
    -0.07
    es
    -0.07
    bach
    -0.07
    ient
    -0.07
    bergen
    -0.07
    reff
    -0.07
    estin
    -0.07
    POSITIVE LOGITS
    undle
    0.07
    足äºĨ
    0.07
    undy
    0.07
    porteur
    0.07
    waktu
    0.06
    igsaw
    0.06
     Pah
    0.06
    tu
    0.06
    quential
    0.06
    äºĨåij¢
    0.06
    Activations Density 0.100%

    No Known Activations