© 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. 46761
    Prev
    Next
    INDEX
    Explanations

    rocket propulsion and engines

    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
     TIFF
    -0.07
    íĦ±
    -0.07
    游走
    -0.07
    ÏģαÏĢε
    -0.07
    å±ħæĺĵ
    -0.07
    å´Ĺ
    -0.06
    æ´»åľ¨
    -0.06
    pres
    -0.06
    èĦijæ¢Ĺ
    -0.06
    .copy
    -0.06
    POSITIVE LOGITS
    çĩĥæĸĻ
    0.14
     propulsion
    0.14
    åıijå°Ħ
    0.12
    çģ«ç®Ń
    0.12
     rocket
    0.12
     rockets
    0.11
     payloads
    0.11
     payload
    0.11
     fuel
    0.11
    fuel
    0.11
    Activations Density 0.058%

    No Known Activations