© 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. 1959
    Prev
    Next
    INDEX
    Explanations

    sequences followed by comma

    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
    	namespace
    -0.10
     Platt
    -0.10
     Hayden
    -0.09
    øy
    -0.09
     inhab
    -0.09
     Cue
    -0.09
     prematurely
    -0.09
     Contest
    -0.09
    âĨ
    -0.09
    Mur
    -0.09
    POSITIVE LOGITS
    alsa
    0.08
    share
    0.07
    gon
    0.07
    lete
    0.07
    .admin
    0.07
    cases
    0.07
     fun
    0.07
     Cond
    0.07
    ish
    0.07
    ivas
    0.07
    Activations Density 0.913%

    No Known Activations