© 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. 57529
    Prev
    Next
    INDEX
    Explanations

    if statements

    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
     doubling
    -0.07
     hal
    -0.07
     den
    -0.07
     Jenn
    -0.06
     Wyoming
    -0.06
    cker
    -0.06
     lady
    -0.06
     Guill
    -0.06
    ahl
    -0.06
     Shane
    -0.06
    POSITIVE LOGITS
    edo
    0.12
    ÑĥÑĩ
    0.11
    /Dk
    0.11
    baz
    0.11
    (--
    0.11
    /stdc
    0.10
    vos
    0.10
    \a
    0.10
    achable
    0.10
     ance
    0.10
    Activations Density 0.015%

    No Known Activations