© 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. 57650
    Prev
    Next
    INDEX
    Explanations

    -er, -ator, -er, -er, -iar, -ers, -ker, -ator, -er, -er

    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
    oid
    -0.09
     Vent
    -0.09
    aba
    -0.09
    -j
    -0.09
    ress
    -0.08
    anno
    -0.08
    ry
    -0.08
     competition
    -0.08
     ventilation
    -0.08
    atical
    -0.08
    POSITIVE LOGITS
    -upper
    0.11
    /rem
    0.11
    /install
    0.09
    /ref
    0.09
    /up
    0.09
    oyer
    0.09
    /down
    0.09
    rch
    0.08
    SEN
    0.08
    ÑģÑı
    0.08
    Activations Density 0.068%

    No Known Activations