© 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. 4501
    Prev
    Next
    INDEX
    Explanations

    "may have" or "can have"

    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
     either
    -0.14
     also
    -0.13
    /or
    -0.12
     everywhere
    -0.11
    also
    -0.11
     neither
    -0.11
     Either
    -0.10
     EITHER
    -0.09
     Also
    -0.09
    Either
    -0.09
    POSITIVE LOGITS
     simply
    0.13
     otherwise
    0.13
    abouts
    0.12
     outright
    0.12
     altogether
    0.12
    phans
    0.11
    otate
    0.11
    ello
    0.11
     simplement
    0.10
    :NO
    0.10
    Activations Density 0.385%

    No Known Activations