© 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. 866
    Prev
    Next
    INDEX
    Explanations

    -type=

    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
    ilen
    -0.11
    nda
    -0.10
    oto
    -0.09
     Sy
    -0.09
     Reco
    -0.09
     gar
    -0.09
     reco
    -0.09
     GX
    -0.09
    umni
    -0.09
     Synd
    -0.09
    POSITIVE LOGITS
    canf
    0.08
    jie
    0.08
    builder
    0.08
    kap
    0.08
    =”
    0.08
     po
    0.08
    rok
    0.08
    wers
    0.08
    .fm
    0.07
     pers
    0.07
    Activations Density 0.099%

    No Known Activations