© 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. 73
    Prev
    Next
    INDEX
    Explanations

    off- followed by hyphenated words

    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
    ¸
    -0.09
    acha
    -0.09
    Forms
    -0.09
    .Pool
    -0.09
    FFFF
    -0.09
    ous
    -0.09
    gon
    -0.09
    aries
    -0.08
    umber
    -0.08
    jin
    -0.08
    POSITIVE LOGITS
    ensively
    0.17
    shoot
    0.15
    /on
    0.14
    beat
    0.14
    loading
    0.13
    icer
    0.13
    entimes
    0.13
    enders
    0.12
    site
    0.12
    stage
    0.12
    Activations Density 0.361%

    No Known Activations