© 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. 4424
    Prev
    Next
    INDEX
    Explanations

    biological defects and phenotypes

    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
     gev
    -0.07
    awan
    -0.07
     soothing
    -0.07
     Walton
    -0.07
    loo
    -0.07
    bew
    -0.07
     Blank
    -0.06
     spiked
    -0.06
    pper
    -0.06
    {{$
    -0.06
    POSITIVE LOGITS
     inability
    0.12
    affected
    0.12
     malformed
    0.12
     compensated
    0.11
     compens
    0.11
     phenotype
    0.11
     affected
    0.11
    -comp
    0.11
     Fatal
    0.10
     defects
    0.10
    Activations Density 0.245%

    No Known Activations