© 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. 3915
    Prev
    Next
    INDEX
    Explanations

    of [number]

    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
    erk
    -0.09
    unta
    -0.08
    اب
    -0.08
     trou
    -0.07
    quiv
    -0.07
    etting
    -0.07
    dge
    -0.07
     Burg
    -0.07
    961
    -0.07
    omb
    -0.07
    POSITIVE LOGITS
    enal
    0.11
     tear
    0.09
    olist
    0.09
    stad
    0.09
     tickets
    0.09
    goo
    0.09
    isu
    0.09
    isko
    0.09
    ädchen
    0.09
    \\.
    0.09
    Activations Density 0.206%

    No Known Activations