© 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. 58314
    Prev
    Next
    INDEX
    Explanations

    size, length, or dimension

    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
    rik
    -0.10
     sop
    -0.09
    utsch
    -0.08
     aggrav
    -0.08
     Horm
    -0.08
    usi
    -0.08
    quette
    -0.08
    enh
    -0.07
    hit
    -0.07
     Oilers
    -0.07
    POSITIVE LOGITS
    /sbin
    0.10
    toi
    0.09
     SSR
    0.08
     Pu
    0.08
     [=
    0.08
    cab
    0.08
    owler
    0.08
    ¼
    0.08
    ouch
    0.08
    kre
    0.08
    Activations Density 0.006%

    No Known Activations