© 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. 304
    Prev
    Next
    INDEX
    Explanations

    explaining processes and methods

    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
     immedi
    -0.08
     majority
    -0.08
     stead
    -0.08
    presence
    -0.08
     presence
    -0.07
     zad
    -0.07
    jem
    -0.07
     Armed
    -0.07
     Lud
    -0.07
     bulky
    -0.07
    POSITIVE LOGITS
     how
    0.22
     ways
    0.20
     why
    0.19
     briefly
    0.19
    how
    0.17
     reasons
    0.16
     tips
    0.15
     examples
    0.15
     details
    0.15
     brief
    0.15
    Activations Density 2.769%

    No Known Activations