© 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. 58576
    Prev
    Next
    INDEX
    Explanations

    sac followed by related words like char, chi, City, rum, ro, ral

    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
    ayne
    -0.10
     Peg
    -0.09
     anon
    -0.09
    olle
    -0.09
    веÑĢ
    -0.09
    lings
    -0.09
    cation
    -0.09
    ī
    -0.09
    stellen
    -0.09
    ruise
    -0.09
    POSITIVE LOGITS
    ramento
    0.10
     unre
    0.08
    sg
    0.08
    Visitor
    0.08
    oman
    0.08
    voke
    0.08
    bian
    0.08
    fully
    0.08
    contro
    0.07
    UPPORT
    0.07
    Activations Density 0.015%

    No Known Activations