© 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. 45763
    Prev
    Next
    INDEX
    Explanations

    parenthesized expressions with trailing symbols

    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
    åĬ¨å®¹
    -0.07
    achable
    -0.07
    å¨ħ
    -0.07
    mlin
    -0.07
    .isDefined
    -0.07
    _tolerance
    -0.06
    离æĪij们
    -0.06
    尽管
    -0.06
    éĺĶ
    -0.06
    éĢĿ
    -0.06
    POSITIVE LOGITS
    unts
    0.08
    eras
    0.06
    Ø·ÙĬÙĨ
    0.06
    adders
    0.06
    æn
    0.06
    åݿ人æ°ijæĶ¿åºľ
    0.06
    æ·ĩ
    0.06
    建å®ī
    0.06
    å¹³åĿĩ
    0.06
    اعات
    0.06
    Activations Density 0.028%

    No Known Activations