© 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. 58235
    Prev
    Next
    INDEX
    Explanations

    communications systems, usr/bin paths

    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
    atri
    -0.09
    eee
    -0.08
    /$
    -0.08
    åħĪ
    -0.08
     tape
    -0.08
    brid
    -0.08
    ner
    -0.08
    plers
    -0.08
    tec
    -0.08
     Rect
    -0.07
    POSITIVE LOGITS
    flux
    0.10
     resolutions
    0.09
    inden
    0.09
    oute
    0.09
    oda
    0.08
     teil
    0.08
    flows
    0.08
     occasional
    0.08
    geme
    0.08
     spe
    0.08
    Activations Density 0.004%

    No Known Activations