© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30587
    Prev
    Next
    INDEX
    Explanations

    oscillation or bouncing

    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
    ÑĪелÑĮ
    -0.09
    oggled
    -0.09
    igy
    -0.08
    _MSK
    -0.08
    西çľģ
    -0.08
    æĶ¹åıĺèĩªå·±
    -0.08
    åıĺæĽ´é¡¹çĽ®
    -0.08
    izio
    -0.08
    èĢ»è¾±
    -0.08
     uniquely
    -0.08
    POSITIVE LOGITS
     oversh
    0.12
     oscill
    0.08
    è¿ĩ头
    0.07
     Osc
    0.07
    åĽ´ç»ķ
    0.07
     osc
    0.07
    åĨ²é«ĺ
    0.06
    osc
    0.06
     magn
    0.06
    hyper
    0.06
    Activations Density 0.003%

    No Known Activations