© 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. 61511
    Prev
    Next
    INDEX
    Explanations

    extra

    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
    iec
    -0.10
    .TryParse
    -0.10
     Buchanan
    -0.10
     (('
    -0.10
    ximity
    -0.10
     plural
    -0.10
    ula
    -0.09
    ģ
    -0.09
    -in
    -0.09
    thinkable
    -0.09
    POSITIVE LOGITS
    cation
    0.09
    ity
    0.09
    cly
    0.08
    thood
    0.08
     ori
    0.08
    ÑĤÑĮ
    0.07
     ado
    0.07
    .override
    0.07
    ular
    0.07
    aires
    0.07
    Activations Density 0.006%

    No Known Activations