© 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. 827
    Prev
    Next
    INDEX
    Explanations

    listing items

    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
    "/
    -0.09
    yx
    -0.08
    dos
    -0.08
    -bound
    -0.08
    <|fim_suffix|>
    -0.08
    picture
    -0.07
    ;y
    -0.07
    ected
    -0.07
     ?.
    -0.07
    ...↵↵↵
    -0.07
    POSITIVE LOGITS
     including
    0.15
     which
    0.12
     particularly
    0.11
     especially
    0.11
     along
    0.11
     albeit
    0.11
     specifically
    0.10
     thereby
    0.10
     plus
    0.10
     whether
    0.10
    Activations Density 1.644%

    No Known Activations