© 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. 64727
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and forms

    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
    ryn
    -0.08
    æºIJ
    -0.08
    asse
    -0.07
    éľį
    -0.07
    ç«ĸåIJij
    -0.06
    å¼Ĥæł·
    -0.06
    [source
    -0.06
     hozzá
    -0.06
    prite
    -0.06
    ynn
    -0.06
    POSITIVE LOGITS
    çĶŁæ°´
    0.08
    ιε
    0.08
    éĢļè¿ĩç½ij绾
    0.08
     geometry
    0.07
    ìĬ¹
    0.07
    .PO
    0.07
    emel
    0.07
    两å¤Ħ
    0.07
    åĩłä½ķ
    0.07
    lug
    0.07
    Activations Density 0.155%

    No Known Activations