© 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. 48568
    Prev
    Next
    INDEX
    Explanations

    help command

    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
    èī¯
    -0.07
    _dirty
    -0.07
    aths
    -0.06
     heck
    -0.06
    emps
    -0.06
    oner
    -0.06
    ä¸įèµ°
    -0.06
    yczy
    -0.06
    umblr
    -0.06
    λά
    -0.06
    POSITIVE LOGITS
    ÙĪدÛĮ
    0.08
    çĥŃæĥħ
    0.08
    apan
    0.07
    许许å¤ļ
    0.07
    æ²»çIJĨèĥ½åĬĽ
    0.07
    åıijçĶŁéĩį大
    0.07
    æĺ¯çľŁ
    0.07
    fran
    0.07
    æģŃåĸľä½ł
    0.07
    çĥŃæĥħçļĦ
    0.07
    Activations Density 0.007%

    No Known Activations