© 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. 54188
    Prev
    Next
    INDEX
    Explanations

    swift, python, go, or other code

    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
     archetype
    -0.10
    ocard
    -0.10
    dal
    -0.09
    ox
    -0.09
    itech
    -0.09
    .Builder
    -0.09
    åįķä½į
    -0.09
     atleast
    -0.09
    lotte
    -0.08
    rtype
    -0.08
    POSITIVE LOGITS
    gard
    0.09
     pov
    0.08
     Undo
    0.08
    ne
    0.08
    ASM
    0.08
     royal
    0.07
    Collapse
    0.07
    stery
    0.07
    chant
    0.07
     subsidy
    0.07
    Activations Density 0.001%

    No Known Activations