© 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. 55361
    Prev
    Next
    INDEX
    Explanations

    restore state

    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
     still
    -0.10
     resumed
    -0.09
     erm
    -0.09
     resumes
    -0.09
     ^=
    -0.08
    Still
    -0.08
     Camden
    -0.08
    ember
    -0.08
     again
    -0.08
     spor
    -0.08
    POSITIVE LOGITS
    kos
    0.10
     Changes
    0.09
     faithfully
    0.09
    umper
    0.08
     changes
    0.08
    ÃŃst
    0.08
     fidelity
    0.08
    ty
    0.08
    -dist
    0.08
     Gael
    0.08
    Activations Density 0.039%

    No Known Activations