© 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. 54482
    Prev
    Next
    INDEX
    Explanations

    Union following place names or 'of'

    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
    ft
    -0.11
    ky
    -0.11
    rix
    -0.11
    upp
    -0.10
    vie
    -0.09
    blick
    -0.09
    .fn
    -0.09
    _helpers
    -0.09
    extr
    -0.09
    (#
    -0.09
    POSITIVE LOGITS
    ized
    0.18
    ism
    0.13
    ists
    0.13
    ically
    0.12
    ist
    0.12
    ised
    0.11
    ical
    0.11
    ista
    0.11
    ed
    0.10
    istic
    0.10
    Activations Density 0.007%

    No Known Activations