© 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. 4132
    Prev
    Next
    INDEX
    Explanations

    java Scanner input

    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
     Dag
    -0.13
    ,eg
    -0.12
    needle
    -0.12
    <!--<
    -0.12
     dov
    -0.12
    dag
    -0.12
     telefon
    -0.11
     )))
    -0.11
     exporter
    -0.11
    .extern
    -0.11
    POSITIVE LOGITS
     congr
    0.07
     prompts
    0.06
     Ter
    0.06
    .Scanner
    0.06
     sabot
    0.06
     hosp
    0.06
     bulletin
    0.06
     terminal
    0.06
     ins
    0.06
     realism
    0.06
    Activations Density 0.514%

    No Known Activations