© 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. 58268
    Prev
    Next
    INDEX
    Explanations

    navigation links and titles

    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
     subt
    -0.09
     Kens
    -0.09
     Carpet
    -0.08
     squeez
    -0.08
     Mature
    -0.08
    ius
    -0.08
     cleared
    -0.08
    alle
    -0.08
    iew
    -0.08
    nty
    -0.07
    POSITIVE LOGITS
     uncert
    0.10
     uncomp
    0.10
    ADA
    0.10
     bath
    0.09
    voices
    0.09
    annya
    0.09
     incarcer
    0.09
    amac
    0.09
    voice
    0.08
     unc
    0.08
    Activations Density 0.002%

    No Known Activations