© 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. 61668
    Prev
    Next
    INDEX
    Explanations

    concentration units (/mL, mM, /L)

    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
     streak
    -0.08
    coat
    -0.07
     exacerb
    -0.07
     %.
    -0.07
    ning
    -0.07
    ous
    -0.07
     Sheldon
    -0.07
    acies
    -0.07
    avin
    -0.07
     devel
    -0.07
    POSITIVE LOGITS
    fas
    0.10
    YE
    0.10
    urator
    0.09
     Engel
    0.09
    egin
    0.09
    ERY
    0.09
    fef
    0.09
     explanatory
    0.09
    rie
    0.09
    .lesson
    0.09
    Activations Density 0.016%

    No Known Activations