© 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. 13174
    Prev
    Next
    INDEX
    Explanations

    vector or list container operations

    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
    ä¸Ģ代
    -0.07
    undas
    -0.07
    rtl
    -0.07
    åı¸ç©º
    -0.07
    ä¿®
    -0.07
    راÙħ
    -0.07
     пÑĢоÑģÑĤÑĥ
    -0.06
    áĥĶáĥijáĥĺáĥĹ
    -0.06
     везде
    -0.06
    PIP
    -0.06
    POSITIVE LOGITS
     containing
    0.09
     ÑģоÑģÑĤоÑı
    0.08
    jango
    0.08
    åĨħéĥ¨çļĦ
    0.08
    åħ»çļĦ
    0.08
     chứa
    0.08
     berisi
    0.08
    stash
    0.08
     size
    0.08
    odb
    0.08
    Activations Density 0.032%

    No Known Activations