© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3256
    Prev
    Next
    INDEX
    Explanations

    magnetic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âļĹ
    -0.22
    opor
    -0.22
    acco
    -0.22
    ialog
    -0.21
    cene
    -0.21
    nex
    -0.21
    oload
    -0.21
    PageRoute
    -0.21
    forgettable
    -0.21
    pson
    -0.21
    POSITIVE LOGITS
    ç£ģåľº
    0.40
    ç£ģ
    0.40
     Magnetic
    0.39
     magnetic
    0.38
    agnetic
    0.33
     magnet
    0.32
    éĵģ
    0.30
     Magnet
    0.29
     magnets
    0.27
    éĴķ
    0.27
    Activations Density 0.519%

    No Known Activations