© 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. 8463
    Prev
    Next
    INDEX
    Explanations

    'i' as an ending

    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
    e
    -0.16
    eer
    -0.14
    een
    -0.14
    а
    -0.14
    ees
    -0.14
    ez
    -0.13
    lopedia
    -0.13
    eon
    -0.13
    eba
    -0.12
    eor
    -0.12
    POSITIVE LOGITS
    i
    0.59
    iya
    0.27
    iou
    0.25
    iÄĩ
    0.24
    iT
    0.23
    iado
    0.23
    iÄį
    0.23
    iare
    0.22
    iens
    0.21
    iode
    0.20
    Activations Density 0.962%

    No Known Activations