© 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. 2236
    Prev
    Next
    INDEX
    Explanations

    section marker {.sec}

    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
    01
    -0.12
    -first
    -0.10
     laying
    -0.10
     ?.
    -0.09
    okin
    -0.09
     [][]
    -0.09
    00
    -0.09
    onet
    -0.09
    1
    -0.09
     first
    -0.09
    POSITIVE LOGITS
    curities
    0.08
    angered
    0.07
    erot
    0.07
    KEN
    0.07
    itored
    0.07
    bee
    0.07
    yd
    0.07
    /tty
    0.06
     ########.
    0.06
    ibur
    0.06
    Activations Density 0.003%

    No Known Activations