© 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. 1610
    Prev
    Next
    INDEX
    Explanations

    approximately half

    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
     essentially
    -0.13
     mere
    -0.12
    lein
    -0.11
     basically
    -0.10
    engl
    -0.10
    jee
    -0.10
    /Search
    -0.10
     merely
    -0.09
    <-
    -0.09
     liá»ĩu
    -0.09
    POSITIVE LOGITS
     dozen
    0.14
     halfway
    0.12
     half
    0.11
     midway
    0.11
     speaking
    0.10
     (?)
    0.10
    imately
    0.10
    aten
    0.09
     synonymous
    0.09
     thousand
    0.08
    Activations Density 1.103%

    No Known Activations