© 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. 526
    Prev
    Next
    INDEX
    Explanations

    version 3 of the license

    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
    nd
    -0.16
    -thirds
    -0.14
    th
    -0.11
    nds
    -0.09
    3
    -0.08
     Dod
    -0.08
    eenth
    -0.08
     relaxing
    -0.08
     inn
    -0.08
    âĶĢ
    -0.08
    POSITIVE LOGITS
    rd
    0.35
    -quarters
    0.26
     rd
    0.18
    RD
    0.16
    fold
    0.13
    DES
    0.13
    (rd
    0.13
    .amazonaws
    0.13
     cheers
    0.13
    quarters
    0.12
    Activations Density 0.869%

    No Known Activations