© 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. 56965
    Prev
    Next
    INDEX
    Explanations

    certain conditions or hypotheses

    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
     Gamb
    -0.11
     Maur
    -0.10
    obe
    -0.10
     Trev
    -0.10
     Ivy
    -0.10
     Certain
    -0.10
     recur
    -0.10
    Incre
    -0.10
    qua
    -0.10
    .central
    -0.10
    POSITIVE LOGITS
     Kro
    0.08
    Ļ
    0.08
     (“
    0.08
     originating
    0.07
     choice
    0.07
     Choice
    0.07
     stil
    0.07
     Gre
    0.06
     CHO
    0.06
     Mobility
    0.06
    Activations Density 0.022%

    No Known Activations