© 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. 30567
    Prev
    Next
    INDEX
    Explanations

    empty or zero values

    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
    rett
    -0.07
    ALS
    -0.06
    omin
    -0.06
    çļĦé¦ĸ
    -0.06
    éĩijä¸Ŀ
    -0.06
    .findById
    -0.06
    åĩºå¥ĩ
    -0.06
    маÑĤо
    -0.06
     Prov
    -0.06
    表çĻ½
    -0.06
    POSITIVE LOGITS
    ä¸ºéĽ¶
    0.16
     zero
    0.15
    鼶
    0.14
     Zero
    0.14
    为空
    0.13
    .zero
    0.13
     Null
    0.12
    _zero
    0.12
    .Zero
    0.12
    EMPTY
    0.12
    Activations Density 0.172%

    No Known Activations