© 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. 96
    Prev
    Next
    INDEX
    Explanations

    programming keywords: declared

    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
    inium
    -0.08
    ography
    -0.07
     così
    -0.06
     lifestyle
    -0.06
    999
    -0.06
    oto
    -0.06
    umpy
    -0.06
    /stretchr
    -0.06
     ener
    -0.05
     nutshell
    -0.05
    POSITIVE LOGITS
     constants
    0.14
     abbrev
    0.13
    "is
    0.12
    Abb
    0.12
     blacklist
    0.12
     misunder
    0.11
    "',↵
    0.11
    ',...↵
    0.11
     dictionaries
    0.11
    "g
    0.11
    Activations Density 1.442%

    No Known Activations