© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56725
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
     Prest
    -0.07
    abee
    -0.07
     Brend
    -0.07
    èĥ
    -0.07
     Stud
    -0.07
     Glas
    -0.07
    feeding
    -0.07
    .DEFAULT
    -0.07
     Circus
    -0.07
    velle
    -0.07
    POSITIVE LOGITS
    enu
    0.09
    cul
    0.09
    amos
    0.08
    izio
    0.08
     rit
    0.08
    fte
    0.08
    accom
    0.08
     Wish
    0.08
     dep
    0.08
    aos
    0.08
    Activations Density 0.106%

    No Known Activations