© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1583
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by names

    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
    asm
    -0.10
    ãĥ³ãĤ°
    -0.09
    äng
    -0.09
    thest
    -0.09
    erable
    -0.09
    iden
    -0.09
    enic
    -0.09
    -thumb
    -0.09
    qp
    -0.09
    esser
    -0.09
    POSITIVE LOGITS
    -century
    0.18
    ousand
    0.15
    -generation
    0.15
     century
    0.14
    -order
    0.14
    -best
    0.13
    -largest
    0.13
    -feira
    0.13
    -ranked
    0.13
    -floor
    0.12
    Activations Density 0.596%

    No Known Activations