© 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. 56407
    Prev
    Next
    INDEX
    Explanations

    how to change

    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
     Qualified
    -0.08
     pier
    -0.07
     ready
    -0.07
     rim
    -0.07
    ner
    -0.07
    ius
    -0.07
     eye
    -0.07
     pending
    -0.07
     ground
    -0.07
    ener
    -0.06
    POSITIVE LOGITS
    Tutorial
    0.12
    abi
    0.12
     cach
    0.11
     Laure
    0.10
    ducted
    0.10
    lock
    0.10
    mdir
    0.10
     getpid
    0.10
     Tutorial
    0.10
    yscale
    0.10
    Activations Density 0.643%

    No Known Activations