© 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. 18359
    Prev
    Next
    INDEX
    Explanations

    minerals and chemical compounds

    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
    hetto
    -0.08
    秫
    -0.07
    osterone
    -0.07
    னி
    -0.07
    天干
    -0.06
    æİĸ
    -0.06
     crossed
    -0.06
    kona
    -0.06
     XXX
    -0.06
    è¯¥ç³»ç»Ł
    -0.06
    POSITIVE LOGITS
    esor
    0.08
    chalk
    0.07
    -opacity
    0.07
    orios
    0.07
    YLE
    0.07
    ело
    0.07
    yles
    0.07
    yle
    0.07
    nock
    0.07
    gne
    0.07
    Activations Density 0.005%

    No Known Activations