© 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. 57200
    Prev
    Next
    INDEX
    Explanations

    webpack, August, economic

    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
    èIJį
    -0.07
     keypad
    -0.07
     IOCTL
    -0.07
    idd
    -0.07
    çľģçļĦ
    -0.06
    å¸Ĥåľºè°ĥæŁ¥
    -0.06
     изве
    -0.06
     Wib
    -0.06
     alphanumeric
    -0.06
    éļıå¿ĥ
    -0.06
    POSITIVE LOGITS
    tape
    0.09
    Fun
    0.08
    ëį
    0.08
    æŀ¶ä¸Ĭ
    0.08
    çĭ¸
    0.07
    haus
    0.07
     functor
    0.07
    çĥ½
    0.07
     Sampling
    0.07
    inata
    0.07
    Activations Density 0.012%

    No Known Activations