© 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. 14860
    Prev
    Next
    INDEX
    Explanations

    base class library

    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
    antum
    -0.07
    çī¹æķĪ
    -0.07
    ä¿±è¿Ľ
    -0.06
    åĩ«
    -0.06
    æľīå¥ĸ
    -0.06
    _histogram
    -0.06
     íĩ´
    -0.06
    tima
    -0.06
    çĽĪçĽĪ
    -0.06
    èĥŃ
    -0.06
    POSITIVE LOGITS
     foundational
    0.16
    åŁºç¡ĢæĢ§
    0.15
     base
    0.14
    /base
    0.13
    åŁºç¡Ģ
    0.13
    å¥łå®ļ
    0.12
     foundation
    0.12
    base
    0.12
    åŁºåºķ
    0.12
    åŁºåľ°
    0.12
    Activations Density 0.176%

    No Known Activations