© 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. 62233
    Prev
    Next
    INDEX
    Explanations

    chaotic trajectories and dynamics

    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
    åħ¶èģĮ
    -0.07
    çŃĶè°¢
    -0.07
    æ±Łè·¯
    -0.07
    ాయి
    -0.07
    æĽĻ
    -0.06
    çµ±ä¸Ģ
    -0.06
    为éļ¾
    -0.06
     headline
    -0.06
    è¿Ļ个æŶåĢĻ
    -0.06
    å§IJ夫
    -0.06
    POSITIVE LOGITS
    ehan
    0.08
     trajectories
    0.08
    åĪĿå§ĭ
    0.08
    ç¯Ħ
    0.07
    trajectory
    0.07
    allee
    0.07
    ouw
    0.07
    ä¸ĢçĽĺ
    0.07
    bang
    0.07
     Initial
    0.07
    Activations Density 0.005%

    No Known Activations