© 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. 30539
    Prev
    Next
    INDEX
    Explanations

    temporal progression or sequence

    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.08
     же
    -0.08
    .yahoo
    -0.08
     Ø®ÙĦاÙĦÙĩا
    -0.08
     nonetheless
    -0.08
    ikk
    -0.08
     moreover
    -0.08
    alent
    -0.07
    ä¹ĭç¥ŀ
    -0.07
    avascript
    -0.07
    POSITIVE LOGITS
    ...
    0.06
    ——
    0.06
    isches
    0.06
    bourne
    0.06
    _bindings
    0.06
    对æīĢ
    0.06
    æĺ¯è¿Ļ个
    0.06
    å°¤åħ¶æĺ¯åľ¨
    0.06
    对è¿Ļ个
    0.06
    对äºİè¿Ļ个
    0.06
    Activations Density 0.905%

    No Known Activations