© 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. 54825
    Prev
    Next
    INDEX
    Explanations

    xml dependency tags

    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
    spl
    -0.11
    ifo
    -0.09
    Ñģли
    -0.09
    reste
    -0.08
    otti
    -0.08
    kish
    -0.08
    交
    -0.08
    reur
    -0.08
    este
    -0.08
    oti
    -0.08
    POSITIVE LOGITS
    idel
    0.10
    æ
    0.09
     POWER
    0.09
    ç
    0.09
     artificially
    0.09
    ent
    0.08
    ano
    0.08
     Crisis
    0.08
    azz
    0.08
     power
    0.08
    Activations Density 0.003%

    No Known Activations