© 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. 8441
    Prev
    Next
    INDEX
    Explanations

    types of specialist applications

    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
    omentum
    -0.10
     honeymoon
    -0.09
    /pm
    -0.08
    /power
    -0.08
    rafted
    -0.08
    _CONST
    -0.08
    EOS
    -0.08
    .Adam
    -0.08
    /head
    -0.08
     hp
    -0.08
    POSITIVE LOGITS
    éné
    0.09
     deleteUser
    0.08
     Specialty
    0.08
    tip
    0.07
     specialised
    0.07
    á»Ĺ
    0.07
    ãĢİ
    0.07
    orte
    0.07
     vintage
    0.07
    datatype
    0.07
    Activations Density 1.234%

    No Known Activations