© 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. 61809
    Prev
    Next
    INDEX
    Explanations

    repeated elements or combinations

    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
    ifel
    -0.08
    akkan
    -0.08
    çľĭå®ĪæīĢ
    -0.07
    éķ·å¤§
    -0.07
    {}'.
    -0.07
     sometime
    -0.07
     EITHER
    -0.07
    èľĵ
    -0.07
    ä¸´æ±Ł
    -0.07
    baran
    -0.07
    POSITIVE LOGITS
    onge
    0.08
    æĺİæĺİ
    0.07
    indo
    0.07
    amed
    0.07
    æľĥä¸Ĭ
    0.06
    ilst
    0.06
    regar
    0.06
    kens
    0.06
    ruise
    0.06
    abay
    0.06
    Activations Density 0.015%

    No Known Activations