© 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. 54112
    Prev
    Next
    INDEX
    Explanations

    html meta tags or android setContentView

    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
    ilton
    -0.09
     Val
    -0.08
     Pot
    -0.08
     cont
    -0.08
    ¯
    -0.08
     Ott
    -0.08
     drum
    -0.07
     Saturday
    -0.07
     subs
    -0.07
     pairs
    -0.07
    POSITIVE LOGITS
    spl
    0.10
    ___↵↵
    0.09
    ")(
    0.09
    /framework
    0.09
    ISTER
    0.09
    iji
    0.09
    loo
    0.09
     Lans
    0.09
    prit
    0.09
    ól
    0.09
    Activations Density 0.014%

    No Known Activations