© 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. 34079
    Prev
    Next
    INDEX
    Explanations

    ferromagnetic and ferroelectric properties

    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
    游åĪĥ
    -0.10
    èĮģ
    -0.09
    .bot
    -0.08
    èĪįå¾Ĺ
    -0.08
    DER
    -0.08
    è¶Ĭèµ°
    -0.08
    Ùģاض
    -0.08
    wiss
    -0.08
     Bot
    -0.08
    uisse
    -0.08
    POSITIVE LOGITS
    ç£ģæĢ§
    0.10
     magnetic
    0.10
     magnet
    0.09
    ç£ģ
    0.08
     Magnetic
    0.07
     magnets
    0.07
     Magnet
    0.07
    agnetic
    0.07
     magn
    0.07
    agnet
    0.06
    Activations Density 0.011%

    No Known Activations