© 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. 54143
    Prev
    Next
    INDEX
    Explanations

    good idea or thing

    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
     necessity
    -0.10
     getopt
    -0.10
    .Null
    -0.10
    sey
    -0.09
    ::<
    -0.09
    lux
    -0.09
     forgiven
    -0.09
     lux
    -0.09
    Null
    -0.09
     convenience
    -0.09
    POSITIVE LOGITS
    amt
    0.08
    unce
    0.07
    amina
    0.07
     lur
    0.07
    mps
    0.07
     Dahl
    0.07
    atts
    0.07
    apon
    0.07
     Gal
    0.07
    markt
    0.06
    Activations Density 0.037%

    No Known Activations