© 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. 50842
    Prev
    Next
    INDEX
    Explanations

    parents and their children

    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
    mdb
    -0.11
    纷åijĪ
    -0.09
    oooooooo
    -0.09
    ered
    -0.09
    大家ä¸Ģèµ·
    -0.08
    ×ķ×ĵ×Ķ
    -0.08
    chai
    -0.08
    رة
    -0.08
    ertz
    -0.08
     Mariano
    -0.08
    POSITIVE LOGITS
    åŃIJ女
    0.09
    esco
    0.08
    ä¹ĭä¸ĢçļĦ
    0.07
    -child
    0.07
     themselves
    0.07
     who
    0.07
    ãĤ²ãĥ³
    0.07
    /
    0.07
    çĪ·çĪ·å¥¶å¥¶
    0.07
    ä¹ĭéŁ³
    0.07
    Activations Density 0.044%

    No Known Activations