© 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. 50501
    Prev
    Next
    INDEX
    Explanations

    reaching saturation or plateau

    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
     conting
    -0.07
    è¶ģçĿĢ
    -0.07
    .deb
    -0.06
    alone
    -0.06
    ä½ĵç³»
    -0.06
    è½½
    -0.06
    æ¢ĵ
    -0.06
     gamb
    -0.06
    ucid
    -0.06
     Fac
    -0.06
    POSITIVE LOGITS
     plateau
    0.12
    å°ģ顶
    0.10
    Reached
    0.09
     reached
    0.09
     saturation
    0.08
     satur
    0.08
    å·²ç»ıè¾¾åĪ°
    0.08
     Reached
    0.08
    plate
    0.08
    ä¸įåīį
    0.08
    Activations Density 0.011%

    No Known Activations