© 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. 27608
    Prev
    Next
    INDEX
    Explanations

    magnet or magnets

    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
    amble
    -0.08
    anvas
    -0.08
    ffset
    -0.07
    à¤ģ
    -0.07
    ledge
    -0.07
    stellen
    -0.07
    ampton
    -0.07
    aptcha
    -0.07
    asar
    -0.07
    æ°´åĻ¨
    -0.07
    POSITIVE LOGITS
    ized
    0.09
     magnets
    0.09
     magnet
    0.09
    agnetic
    0.09
    ç£ģæĢ§
    0.09
    agnet
    0.08
     Magnet
    0.08
    пÑĢеÑģÑģ
    0.08
    ically
    0.08
    omotive
    0.08
    Activations Density 0.014%

    No Known Activations