© 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. 39135
    Prev
    Next
    INDEX
    Explanations

    full row rank matrix dimensions

    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
    讳
    -0.08
    è¨
    -0.07
    hud
    -0.07
    obr
    -0.07
    çIJIJ
    -0.07
    áŀ½
    -0.07
    aver
    -0.07
    hone
    -0.07
     Mức
    -0.07
     incident
    -0.07
    POSITIVE LOGITS
    个头
    0.08
     outnumber
    0.07
    /max
    0.07
     dimensional
    0.07
    éĴī
    0.07
    纵çĦ¶
    0.07
    -sized
    0.07
    IDGET
    0.07
     McKin
    0.07
     dimension
    0.07
    Activations Density 0.007%

    No Known Activations