© 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. 47167
    Prev
    Next
    INDEX
    Explanations

    magnetic nanoparticles Fe3O4

    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
    onia
    -0.08
    urut
    -0.07
    mailer
    -0.07
    ä¸į设
    -0.07
    anci
    -0.07
    bö
    -0.07
    psilon
    -0.07
    ä¸Ģ对ä¸Ģ
    -0.07
    amping
    -0.07
    æİĴéĺŁ
    -0.07
    POSITIVE LOGITS
    zec
    0.07
    æĢ»åĮ»éĻ¢
    0.06
    rete
    0.06
    eningen
    0.06
    aises
    0.06
    ä¿Ĺ称
    0.06
    aveled
    0.06
    cts
    0.06
    sync
    0.06
    azione
    0.06
    Activations Density 0.006%

    No Known Activations