© 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. 57185
    Prev
    Next
    INDEX
    Explanations

    inf + words like ation, usion, using, erring

    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
    ely
    -0.10
    fully
    -0.09
    inner
    -0.09
    ewe
    -0.09
    ège
    -0.08
    Ñĥн
    -0.08
     disconnect
    -0.08
    Ĺı
    -0.08
     sandwich
    -0.08
     Tul
    -0.08
    POSITIVE LOGITS
    ings
    0.10
     Raum
    0.09
    ели
    0.09
    estation
    0.08
    inged
    0.08
    ing
    0.08
    -inf
    0.08
    nf
    0.08
    amy
    0.08
    leur
    0.08
    Activations Density 0.011%

    No Known Activations