© 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. 41612
    Prev
    Next
    INDEX
    Explanations

    paths and pathways

    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
    åīįåIJİçļĦ
    -0.07
    æĻĵ举
    -0.07
     Russo
    -0.07
    .phase
    -0.07
    åīįå¾Į
    -0.07
    æĸ°ä¸Ģ
    -0.07
    stage
    -0.07
    éĺ¶æ®µçļĦ
    -0.07
    stellen
    -0.07
    eliz
    -0.07
    POSITIVE LOGITS
    è·¯å¾Ħ
    0.13
     paths
    0.12
    éĢĶå¾Ħ
    0.12
    路线
    0.12
    为主线
    0.12
     pathway
    0.11
     pathways
    0.11
     path
    0.11
    å§ĭäºİ
    0.11
    ãĥ«ãĥ¼ãĥĪ
    0.10
    Activations Density 0.066%

    No Known Activations