© 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. 3756
    Prev
    Next
    INDEX
    Explanations

    sequences like "Step", "Block", "group", "test"

    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
    æĤ¨æīĢ
    -0.06
    reif
    -0.06
    Ù°
    -0.06
    gai
    -0.06
    çŃīå¤ļç§įå½¢å¼ı
    -0.06
    ilea
    -0.06
    对æĤ¨
    -0.06
     wherever
    -0.05
    æĬĹåĩ»çĸ«æĥħ
    -0.05
    Ö¼
    -0.05
    POSITIVE LOGITS
    èĢ³çĨŁèĥ½è¯¦
    0.10
    身临åħ¶å¢ĥ
    0.10
    äºĭåįĬåĬŁåĢį
    0.09
    è·ĥè·ĥ欲è¯ķ
    0.09
    .TryParse
    0.09
     zaÅĽ
    0.08
    ä»»ä½ķåħ¶ä»ĸ
    0.08
     taas
    0.08
     voici
    0.08
    åħ¨å¿ĥåħ¨æĦı
    0.08
    Activations Density 0.106%

    No Known Activations