© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3403
    Prev
    Next
    INDEX
    Explanations

    The ` or ` -

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    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
    mb
    -0.12
     sola
    -0.11
    озв
    -0.10
     Bild
    -0.10
     '~/
    -0.10
     Wr
    -0.10
    loser
    -0.10
     based
    -0.10
    ug
    -0.10
    kos
    -0.10
    POSITIVE LOGITS
     seeming
    0.07
     Desired
    0.07
     desired
    0.07
     whom
    0.07
    å¾ħ
    0.06
     beforehand
    0.06
    dictions
    0.06
    ju
    0.06
    è¦ģ
    0.06
    draw
    0.06
    Activations Density 0.053%

    No Known Activations