© 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. 21633
    Prev
    Next
    INDEX
    Explanations

    deep breath

    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
    è¾īæĺł
    -0.08
    æļ´èºģ
    -0.08
    rawler
    -0.08
    ÙħاÙĩ
    -0.08
    rices
    -0.08
     hashCode
    -0.07
    彬彬
    -0.07
    ÑĩаÑģ
    -0.07
    ãģ°ãĤĵ
    -0.07
     brill
    -0.07
    POSITIVE LOGITS
     breath
    0.13
     breathing
    0.13
    åij¼åIJ¸
    0.12
    åIJ¸æ°Ķ
    0.12
    åij¼æ°Ķ
    0.12
    bre
    0.11
     breathe
    0.11
    æ·±åij¼åIJ¸
    0.11
    åIJ¸åħ¥
    0.11
     inhal
    0.11
    Activations Density 0.022%

    No Known Activations