© 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. 46907
    Prev
    Next
    INDEX
    Explanations

    word in sentence: awaiting

    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
    iette
    -0.07
    erah
    -0.07
    大åIJį
    -0.07
    iram
    -0.06
    วย
    -0.06
    ChangeEvent
    -0.06
    èģĶ社
    -0.06
    utel
    -0.06
    umos
    -0.06
    atz
    -0.06
    POSITIVE LOGITS
    á»±c
    0.07
    ilha
    0.07
    éĴ³
    0.06
    edés
    0.06
    éĩij森
    0.06
    nowled
    0.06
    åľ¨ä¸Ĭè¿°
    0.06
    าà¸Ļà¸Ħร
    0.06
    ä¸įè¿ĺ
    0.06
     Mil
    0.06
    Activations Density 0.028%

    No Known Activations