© 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. 43432
    Prev
    Next
    INDEX
    Explanations

    – followed by location names

    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
    emente
    -0.10
    apas
    -0.08
    asai
    -0.07
    ÚĺÛĮ
    -0.07
    æĿ¾æŁı
    -0.07
    asi
    -0.07
    edan
    -0.07
    elos
    -0.07
    诸
    -0.07
    -sama
    -0.07
    POSITIVE LOGITS
    é¾Ħ
    0.07
    mann
    0.07
    æĨ¬
    0.07
    åĪ¶å®ľ
    0.07
    enhagen
    0.07
    ney
    0.06
    ington
    0.06
    à®®à¯ģ
    0.06
    ä¹ĻåıĮæĸ¹
    0.06
    IED
    0.06
    Activations Density 0.457%

    No Known Activations