© 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. 56586
    Prev
    Next
    INDEX
    Explanations

    .github

    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
    -bordered
    -0.11
     Mell
    -0.10
    nant
    -0.09
     Chew
    -0.09
     Proud
    -0.09
     Kata
    -0.09
    ume
    -0.09
    /from
    -0.09
    ä¹
    -0.09
    /testify
    -0.09
    POSITIVE LOGITS
    hoe
    0.08
     humming
    0.07
    hey
    0.07
    qv
    0.07
     abundance
    0.07
     Carlson
    0.07
     dim
    0.07
     getattr
    0.06
     Sor
    0.06
    ery
    0.06
    Activations Density 0.001%

    No Known Activations