© 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. 57968
    Prev
    Next
    INDEX
    Explanations

    cheer related words

    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
    å¼ı
    -0.12
    ations
    -0.11
     sack
    -0.10
    zug
    -0.10
     sheer
    -0.09
     Bris
    -0.09
    uche
    -0.09
     Huff
    -0.09
    dorf
    -0.09
    -shell
    -0.09
    POSITIVE LOGITS
    fulness
    0.10
    fully
    0.10
    leading
    0.09
    leaders
    0.08
    pone
    0.08
    leader
    0.08
    iable
    0.08
    iev
    0.08
    yped
    0.07
    ych
    0.07
    Activations Density 0.002%

    No Known Activations