© 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. 3484
    Prev
    Next
    INDEX
    Explanations

    first

    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
    nett
    -0.08
    ((((
    -0.08
    orage
    -0.07
     Ratings
    -0.07
    allo
    -0.07
    olf
    -0.07
     penc
    -0.06
     Roller
    -0.06
    лÑĮÑĤ
    -0.06
    poke
    -0.06
    POSITIVE LOGITS
     original
    0.11
     implementations
    0.11
    lex
    0.11
    enga
    0.11
     originals
    0.11
     typical
    0.10
     incarnation
    0.10
     dozen
    0.10
     founding
    0.10
     eccentric
    0.10
    Activations Density 0.664%

    No Known Activations