© 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. 50204
    Prev
    Next
    INDEX
    Explanations

    conditional branches (if/then/else)

    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
    apol
    -0.08
     tâche
    -0.07
    uds
    -0.07
    åıªè¦ģæĺ¯
    -0.07
    è·¯éĢı
    -0.07
    鼶件
    -0.07
    ãĥ¼ãĥĦ
    -0.07
    以任ä½ķ
    -0.07
    æĢİä¹Īçľĭ
    -0.07
    ä¹ĭéģ¥
    -0.07
    POSITIVE LOGITS
    ä¸įéĢĤçĶ¨
    0.08
    Else
    0.08
     Neg
    0.08
    vall
    0.08
    éĢĤçĶ¨
    0.08
    款
    0.07
     Else
    0.07
    arel
    0.07
     subsection
    0.07
    inha
    0.07
    Activations Density 0.016%

    No Known Activations