© 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. 2630
    Prev
    Next
    INDEX
    Explanations

    ization or iation

    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
    ally
    -0.13
    ively
    -0.13
    antly
    -0.12
    ingly
    -0.12
    ably
    -0.11
    ially
    -0.11
    ically
    -0.10
    ely
    -0.10
    opus
    -0.10
    uously
    -0.10
    POSITIVE LOGITS
    ization
    0.21
    isation
    0.18
    ening
    0.14
    åĮĸ
    0.14
    iation
    0.13
    IZATION
    0.13
    ination
    0.13
    ivation
    0.12
    ification
    0.12
    mentation
    0.12
    Activations Density 0.721%

    No Known Activations