© 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. 3672
    Prev
    Next
    INDEX
    Explanations

    delay 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
    åĻĮ
    -0.07
    æĺ¥ç¬ĭ
    -0.07
    ĤŃ
    -0.07
    |int
    -0.07
    ród
    -0.07
     kata
    -0.07
    ãģªãģķ
    -0.06
    athe
    -0.06
    ãĥģãĥ£ãĥ³ãĥįãĥ«
    -0.06
    à´¶
    -0.06
    POSITIVE LOGITS
    lag
    0.08
    oker
    0.08
     shift
    0.07
    移è¡Į
    0.07
    ç©
    0.07
    Shift
    0.07
    orro
    0.07
    æľ¬æł¼
    0.07
    hift
    0.07
    _stub
    0.07
    Activations Density 0.002%

    No Known Activations