© 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. 58347
    Prev
    Next
    INDEX
    Explanations

    conditional code blocks

    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
    quist
    -0.08
    chie
    -0.08
     Mai
    -0.07
     loaded
    -0.07
     hap
    -0.07
    mai
    -0.07
    kers
    -0.07
     Uh
    -0.07
     instinct
    -0.07
     regions
    -0.07
    POSITIVE LOGITS
    chet
    0.11
    atto
    0.10
    .byte
    0.10
    Aux
    0.10
    urring
    0.09
    ilha
    0.09
     invade
    0.09
    ableView
    0.09
    roid
    0.09
    aise
    0.09
    Activations Density 0.097%

    No Known Activations