© 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. 4201
    Prev
    Next
    INDEX
    Explanations

    attributes, specifications, characteristics

    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
     Mig
    -0.08
    Disclaimer
    -0.07
     gon
    -0.07
    ark
    -0.06
     visibly
    -0.06
     Interaction
    -0.06
     busy
    -0.06
     Ches
    -0.06
     Sylv
    -0.06
    plier
    -0.06
    POSITIVE LOGITS
     parameters
    0.21
     Parameters
    0.19
     characteristics
    0.18
     Characteristics
    0.18
    Parameters
    0.17
     attributes
    0.16
     specifications
    0.16
     Attributes
    0.16
    parameters
    0.16
    Properties
    0.15
    Activations Density 0.882%

    No Known Activations