© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    fatigue, cycles, and repetition

    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
     اعتÙħاد
    -0.07
    温度计
    -0.07
    rix
    -0.07
    å±ħé«ĺ
    -0.07
    aux
    -0.06
    å®ıè§Ĥè°ĥæݧ
    -0.06
    RIX
    -0.06
     Unblock
    -0.06
    é«ĺå¯Ĩ度
    -0.06
     teleport
    -0.06
    POSITIVE LOGITS
    çĸ²åĬ³
    0.11
     fatigue
    0.11
     endurance
    0.11
     cycle
    0.10
     cycles
    0.09
    orros
    0.09
     Cycle
    0.09
    èĢIJåĬĽ
    0.09
     cycling
    0.08
    å¤ļå°ij次
    0.08
    Activations Density 0.012%

    No Known Activations