© 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. 3854
    Prev
    Next
    INDEX
    Explanations

    primary

    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
     пеÑĢ
    -0.07
    killer
    -0.07
    Checks
    -0.07
    _checker
    -0.07
     simult
    -0.07
    >Last
    -0.07
     reins
    -0.07
    anan
    -0.06
     switched
    -0.06
    NA
    -0.06
    POSITIVE LOGITS
     primary
    0.12
     initial
    0.11
     PRIMARY
    0.11
     ì²
    0.10
    .primary
    0.10
     initially
    0.10
     Primary
    0.10
    PRIMARY
    0.10
    _primary
    0.10
     first
    0.10
    Activations Density 0.403%

    No Known Activations