© 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. 54256
    Prev
    Next
    INDEX
    Explanations

    reserved keyword or identifier

    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
    yb
    -0.10
     welcomes
    -0.09
    iken
    -0.09
     wy
    -0.09
    aro
    -0.09
     ratt
    -0.09
     flag
    -0.09
    upe
    -0.08
    _flags
    -0.08
    oman
    -0.08
    POSITIVE LOGITS
    ogl
    0.09
    rok
    0.08
     reserved
    0.08
    roy
    0.08
     abandonment
    0.08
    bet
    0.08
     chose
    0.08
    _ready
    0.08
     conflict
    0.07
    ade
    0.07
    Activations Density 0.102%

    No Known Activations