© 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. 9791
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    auge
    -0.08
    oga
    -0.07
    aina
    -0.07
    ieso
    -0.07
    omp
    -0.07
    note
    -0.07
    /embed
    -0.07
    è¿Ļçķª
    -0.07
    å¾Ģå¾Ģä¼ļ
    -0.07
    ock
    -0.07
    POSITIVE LOGITS
    åħĨ
    0.08
    åĻ©
    0.07
    à¹Ģรืà¹Īà¸Ńà¸ĩà¸Ĺีà¹Ī
    0.06
    è¡Įç¨ĭ
    0.06
    ople
    0.06
    ÑģмоÑĤÑĢÑı
    0.06
    æīĵæİī
    0.06
    ãģĨãģ¡ãģ«
    0.06
    aversal
    0.06
    sono
    0.06
    Activations Density 0.000%

    No Known Activations