© 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. 2208
    Prev
    Next
    INDEX
    Explanations

    advertisements and continuities

    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
    al
    -0.17
    ive
    -0.16
    ful
    -0.14
    shire
    -0.13
    er
    -0.12
    plier
    -0.12
    VILLE
    -0.12
    ic
    -0.12
    FUL
    -0.11
    y
    -0.11
    POSITIVE LOGITS
    ities
    0.30
    ments
    0.21
    ations
    0.19
    ures
    0.17
    ions
    0.17
    ences
    0.16
    ics
    0.15
    ies
    0.15
    ctions
    0.15
    als
    0.14
    Activations Density 0.599%

    No Known Activations