© 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. 23725
    Prev
    Next
    INDEX
    Explanations

    dark matter

    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
    ÙħÙĪ
    -0.07
    hem
    -0.07
    æŬ
    -0.07
    åĴ²
    -0.07
    dia
    -0.07
    æħĪ禧
    -0.06
    pagen
    -0.06
     Matrix
    -0.06
     pH
    -0.06
     Napole
    -0.06
    POSITIVE LOGITS
    ç²ĴåŃIJ
    0.10
    缨
    0.08
     repositories
    0.08
    kler
    0.08
    å¯Ĩ度
    0.08
    大åĬŁ
    0.08
     Kandid
    0.08
    Crypt
    0.08
    çī©çIJĨåѦ
    0.08
     tunnels
    0.07
    Activations Density 0.014%

    No Known Activations