© 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. 22915
    Prev
    Next
    INDEX
    Explanations

    predicting response or outcome

    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
    æ»ĵ
    -0.07
     definition
    -0.07
    æ¥Ķ
    -0.07
    éħ
    -0.07
    egas
    -0.07
    è´ħ
    -0.07
    definition
    -0.07
    æłĩè¯Ĩçłģ
    -0.07
    æĺİç¡®è§Ħå®ļ
    -0.07
    perse
    -0.07
    POSITIVE LOGITS
     predict
    0.11
     predicting
    0.11
     predicts
    0.11
    é¢Ħæµĭ
    0.11
     Predict
    0.11
    _predict
    0.10
     future
    0.10
    Predict
    0.10
    .predict
    0.10
    predict
    0.09
    Activations Density 0.171%

    No Known Activations