© 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. 56545
    Prev
    Next
    INDEX
    Explanations

    code statements and 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
    æĶ¶äºİ
    -0.07
    æĢİæł·åģļ
    -0.07
    lande
    -0.07
    uckles
    -0.07
    Pod
    -0.07
    _sku
    -0.07
    IndexChanged
    -0.07
    uckland
    -0.07
    å®ŀå¤Ħ
    -0.07
    .dds
    -0.07
    POSITIVE LOGITS
     calls
    0.07
    ׼ף
    0.07
     else
    0.07
    Äĥt
    0.07
    å¤©æ±ł
    0.06
    ä¸Ģç³»åĪĹ
    0.06
    çĦ¶åIJİå°±
    0.06
    æıı
    0.06
    alani
    0.06
    èĽ
    0.06
    Activations Density 0.088%

    No Known Activations