© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 74
    Prev
    Next
    INDEX
    Explanations

    assessing and evaluation

    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
    tn
    -0.07
    ality
    -0.07
    .paths
    -0.06
    christ
    -0.06
     genesis
    -0.06
    iers
    -0.06
    lining
    -0.06
    erchant
    -0.06
     closets
    -0.06
    GS
    -0.06
    POSITIVE LOGITS
    /cal
    0.15
    /me
    0.13
    uator
    0.12
    uated
    0.12
    bane
    0.12
    /check
    0.11
    lops
    0.11
    /design
    0.10
    enance
    0.10
     whether
    0.10
    Activations Density 1.310%

    No Known Activations