© 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. 4178
    Prev
    Next
    INDEX
    Explanations

    about network names and types

    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
    ographies
    -0.08
    oes
    -0.08
     stride
    -0.08
    otope
    -0.07
    width
    -0.07
    ey
    -0.07
     Glen
    -0.07
    OSH
    -0.07
    ahoo
    -0.07
    ook
    -0.07
    POSITIVE LOGITS
     anyway
    0.16
     itself
    0.16
     anyways
    0.15
     indeed
    0.14
     themselves
    0.13
     actually
    0.13
     anyhow
    0.13
     herself
    0.12
     himself
    0.10
     Indeed
    0.10
    Activations Density 0.304%

    No Known Activations