© 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. 40648
    Prev
    Next
    INDEX
    Explanations

    state machine

    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
    umen
    -0.08
    ÑĪеÑĢ
    -0.08
     Daya
    -0.08
     szt
    -0.07
    Scaler
    -0.07
    zinho
    -0.07
    éĶĭèĬĴ
    -0.07
    obox
    -0.07
    ĴĪ
    -0.07
    ÏĦί
    -0.07
    POSITIVE LOGITS
    çĬ¶æĢģ
    0.14
    çĬ¶æĢģçļĦ
    0.13
     state
    0.13
     getState
    0.13
    state
    0.12
    -state
    0.12
    çļĦçĬ¶æĢģ
    0.12
    çĭĢæħĭ
    0.11
     states
    0.11
     State
    0.10
    Activations Density 0.084%

    No Known Activations