© 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. 62648
    Prev
    Next
    INDEX
    Explanations

    aluminum and aluminium

    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
    lettes
    -0.08
    omi
    -0.08
    odyn
    -0.08
    klen
    -0.07
    lessly
    -0.07
    afx
    -0.07
    ork
    -0.07
    loe
    -0.07
    fully
    -0.07
    æīĵæ°Ķ
    -0.07
    POSITIVE LOGITS
    ingen
    0.09
     aluminium
    0.08
     aluminum
    0.08
    éĵĿ
    0.08
     Aluminium
    0.08
     Gujarat
    0.08
     Aluminum
    0.07
     алÑİмин
    0.07
    é»Ħ页
    0.07
    zim
    0.07
    Activations Density 0.015%

    No Known Activations