© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    rangayan or soffi

    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
     minded
    -0.08
    Tags
    -0.08
     Lub
    -0.08
     Locator
    -0.07
    .Range
    -0.07
    isci
    -0.07
    amate
    -0.07
     Bik
    -0.07
    chant
    -0.07
    izard
    -0.07
    POSITIVE LOGITS
    atchewan
    0.12
     mies
    0.09
    loon
    0.09
    owany
    0.09
    olatile
    0.09
    anka
    0.09
    .amazonaws
    0.09
    ool
    0.09
     sadd
    0.09
    fra
    0.09
    Activations Density 0.486%

    No Known Activations