© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20789
    Prev
    Next
    INDEX
    Explanations

    restless, idle, or anxious actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įå¿į
    -0.06
    çŀ¬æŶ
    -0.06
    amá
    -0.06
    ahi
    -0.06
    upakan
    -0.06
    utupan
    -0.06
    é¦Ĵ头
    -0.05
    ä¸ŃæĭĽ
    -0.05
    Orient
    -0.05
     Instantiate
    -0.05
    POSITIVE LOGITS
    æĤ£
    0.06
    踱
    0.06
    lest
    0.06
     restless
    0.06
     idle
    0.05
    åĬ¡
    0.05
    idle
    0.05
    åĬ¨èį¡
    0.05
    磨
    0.05
    Idle
    0.05
    Activations Density 0.005%

    No Known Activations