© 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. 22241
    Prev
    Next
    INDEX
    Explanations

    box and other constraints

    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
    缸éļĶ
    -0.06
     hao
    -0.06
    æĢ»èĥ½
    -0.06
     Strom
    -0.06
     Masih
    -0.06
    adb
    -0.06
    缸åħ³æ³ķå¾ĭ责任
    -0.06
    æĹłéĹ´
    -0.06
    èĬ±èIJ½
    -0.06
    mert
    -0.06
    POSITIVE LOGITS
    约æĿŁ
    0.09
    .constraints
    0.08
    بد
    0.08
     constraints
    0.07
    constraints
    0.07
    amak
    0.07
    è¯ı
    0.07
     restrictions
    0.07
     ìłľìķ½
    0.07
    ToBounds
    0.07
    Activations Density 0.003%

    No Known Activations