© 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. 40174
    Prev
    Next
    INDEX
    Explanations

    tabular data formats

    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
    纵çĦ¶
    -0.08
    erm
    -0.08
    iola
    -0.08
    à§ĩà¦ķ
    -0.07
    éĿ¢åīį
    -0.07
    ike
    -0.07
    anes
    -0.06
    人大
    -0.06
    iori
    -0.06
    reten
    -0.06
    POSITIVE LOGITS
    <tbody
    0.07
    ulp
    0.07
    amento
    0.07
    øb
    0.07
    bourg
    0.06
    оÑĤов
    0.06
    ä¸įä¹°
    0.06
    BLE
    0.06
    plit
    0.06
    ég
    0.06
    Activations Density 0.004%

    No Known Activations