© 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. 1263
    Prev
    Next
    INDEX
    Explanations

    overall goal

    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
    ker
    -0.09
    iro
    -0.09
    apel
    -0.08
    sey
    -0.08
    dro
    -0.08
     particular
    -0.08
    iros
    -0.08
    ewe
    -0.08
    &action
    -0.08
    aks
    -0.08
    POSITIVE LOGITS
    /general
    0.16
    -purpose
    0.16
    -ranging
    0.14
    /global
    0.13
     across
    0.13
     Across
    0.12
    /system
    0.12
     encompass
    0.11
    -wide
    0.11
    Across
    0.11
    Activations Density 1.433%

    No Known Activations