© 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. 16868
    Prev
    Next
    INDEX
    Explanations

    distance, proximity, and scale

    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
    Partition
    -0.08
     proh
    -0.08
    partition
    -0.07
     partition
    -0.07
     Partition
    -0.07
    edef
    -0.07
    èĢIJåĬ³
    -0.07
     partitions
    -0.06
    uards
    -0.06
    ÑĤим
    -0.06
    POSITIVE LOGITS
     distance
    0.11
    çļĦè·Ŀ离
    0.11
    è·ĿéĽ¢
    0.11
    è·Ŀ离
    0.10
    distance
    0.10
     distances
    0.10
    Distance
    0.09
     Distance
    0.09
     ÑĢаÑģÑģÑĤоÑı
    0.09
    éģ¥è¿ľ
    0.08
    Activations Density 0.011%

    No Known Activations