© 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. 57384
    Prev
    Next
    INDEX
    Explanations

    radio station broadcasts

    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
    enco
    -0.09
    åĩĮ
    -0.07
    amil
    -0.07
    æĵį
    -0.07
     vyp
    -0.07
    ëŀ
    -0.07
    å²ij
    -0.07
    æĵįçĽĺ
    -0.06
    Opera
    -0.06
     запÑĢа
    -0.06
    POSITIVE LOGITS
     rare
    0.08
    öss
    0.07
     mainly
    0.07
     mostly
    0.07
    æĸ¹å¼ı为
    0.07
    WithValue
    0.07
     transitions
    0.07
    iley
    0.07
    idah
    0.07
    çİĩè¾¾
    0.07
    Activations Density 0.008%

    No Known Activations