© 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. 27926
    Prev
    Next
    INDEX
    Explanations

    radio transmissions and frequencies

    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
     scaffold
    -0.08
    èĦļæīĭæŀ¶
    -0.07
    èıĮ
    -0.07
    herme
    -0.07
    æĿIJæĸĻåıĬ
    -0.07
     ÑĢеÑģÑĤ
    -0.07
    æŁĦ
    -0.07
    ä¸įèĭŁ
    -0.07
    Frozen
    -0.07
    embro
    -0.07
    POSITIVE LOGITS
     radio
    0.14
     Radio
    0.13
    Radio
    0.13
    æĹłçº¿çĶµ
    0.13
    radio
    0.13
     transmitting
    0.12
    çĶµåı°
    0.12
     frequencies
    0.12
    -radio
    0.12
     transmissions
    0.11
    Activations Density 0.397%

    No Known Activations