© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54015
    Prev
    Next
    INDEX
    Explanations

    for loops and keywords

    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
    arty
    -0.08
    gon
    -0.08
     ...\
    -0.07
     Ba
    -0.07
    ural
    -0.07
    /bar
    -0.07
     strugg
    -0.07
    ester
    -0.07
    /non
    -0.07
    ZN
    -0.07
    POSITIVE LOGITS
    cad
    0.12
    weis
    0.10
    Accepted
    0.10
    ISCO
    0.10
    wich
    0.09
    mut
    0.09
    gw
    0.09
     Cah
    0.09
     skip
    0.09
    auge
    0.09
    Activations Density 0.002%

    No Known Activations