© 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. 51105
    Prev
    Next
    INDEX
    Explanations

    likely probability of events

    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
    attes
    -0.08
    å¯¹æľªæĿ¥
    -0.07
    è¦ģä¸įè¦ģ
    -0.07
    .Loader
    -0.07
    æĺİæĹ¥
    -0.07
    对æīĢ
    -0.07
    å¯¹é¡¹çĽ®
    -0.07
     ÙĦÙĦÙħØ´
    -0.07
    .modify
    -0.07
    /=
    -0.07
    POSITIVE LOGITS
     probably
    0.23
     likely
    0.23
    probably
    0.21
    å¾Īåı¯èĥ½
    0.20
    likely
    0.20
     probable
    0.20
     Likely
    0.20
     probabilmente
    0.19
     probablemente
    0.19
     provavelmente
    0.18
    Activations Density 1.598%

    No Known Activations