© 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. 43085
    Prev
    Next
    INDEX
    Explanations

    topics related to finance and law

    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
    asiun
    -0.09
    çĮľä½łåĸľæ¬¢
    -0.09
    åħ¨éĥ¨è¯Ħ论
    -0.08
    èµĦæĸĻä¸ĭè½½
    -0.08
    žd
    -0.07
    eries
    -0.07
    å±ķå¼Ģåħ¨æĸĩ
    -0.07
    lavier
    -0.07
    atoon
    -0.07
    ettato
    -0.07
    POSITIVE LOGITS
     however
    0.13
     therefore
    0.12
    however
    0.12
     inoltre
    0.10
     thus
    0.10
    åĽłæѤ
    0.09
     же
    0.09
     bowiem
    0.09
    ä¹ŁåĽłæѤ
    0.08
     azonban
    0.08
    Activations Density 0.367%

    No Known Activations