© 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. 42575
    Prev
    Next
    INDEX
    Explanations

    zinc, nonferrous metals, coating

    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
    fü
    -0.07
    è¿ĶãģĹ
    -0.07
    YO
    -0.07
     vidé
    -0.07
     Jam
    -0.07
    Jam
    -0.07
    çĪ
    -0.07
     Latin
    -0.06
     fidel
    -0.06
    precedented
    -0.06
    POSITIVE LOGITS
    çªĿ
    0.08
    adak
    0.08
     nearby
    0.08
    åħ±å¤Ħ
    0.07
    ookie
    0.07
    æŃ
    0.07
    èĩªåıij
    0.07
    elijkheid
    0.07
     espont
    0.07
    çĤ¹ä½į
    0.07
    Activations Density 0.002%

    No Known Activations