© 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. 45820
    Prev
    Next
    INDEX
    Explanations

    arcade version

    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
    /
    -0.07
    æĭĶ
    -0.06
    ete
    -0.06
     Alessandra
    -0.06
    åħ¼
    -0.06
    丫
    -0.06
    Ķ
    -0.06
    ä¸Ģæ´¾
    -0.06
    å¤ļ
    -0.06
     functional
    -0.06
    POSITIVE LOGITS
    é¾Ļæ¹¾
    0.08
    parg
    0.08
    ãi
    0.08
    runner
    0.08
    tow
    0.08
    _td
    0.08
    ipot
    0.08
    lott
    0.08
    utzer
    0.08
    osso
    0.08
    Activations Density 0.030%

    No Known Activations