© 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. 23581
    Prev
    Next
    INDEX
    Explanations

    position followed by words like 'of', 'in', 'from'

    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
    voud
    -0.10
    ä¹ĭè¾Ī
    -0.09
    entication
    -0.08
    feuille
    -0.08
    ÙĬدÙĩ
    -0.08
    irez
    -0.08
    udge
    -0.08
    ç¨ĭ度
    -0.08
    uration
    -0.07
    issement
    -0.07
    POSITIVE LOGITS
    nement
    0.09
    åĴĮä½ľçĶ¨
    0.08
    ities
    0.08
    nalité
    0.08
    ational
    0.08
    SSIP
    0.08
    ality
    0.08
    weise
    0.08
    ings
    0.08
    ately
    0.07
    Activations Density 0.043%

    No Known Activations