© 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. 9257
    Prev
    Next
    INDEX
    Explanations

    magnetic field and quantum effects

    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
    anzi
    -0.07
    æįŁçĽĬ
    -0.06
    å³»
    -0.06
    evity
    -0.06
    åĢ¡
    -0.06
    使çĶ¨éģĵåħ·
    -0.06
     Cartagena
    -0.06
     marine
    -0.06
    pel
    -0.06
    åľºæ¬¡
    -0.06
    POSITIVE LOGITS
    emn
    0.09
    agnetic
    0.09
    ç£ģ
    0.09
    ç´
    0.08
     confinement
    0.08
    è©©
    0.08
    otron
    0.08
     magnetic
    0.08
     Magnetic
    0.08
    æ³ķæĭī
    0.08
    Activations Density 0.007%

    No Known Activations