© 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. 54397
    Prev
    Next
    INDEX
    Explanations

    Java code and questions

    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
    /man
    -0.08
    ulator
    -0.08
    uv
    -0.08
     interstate
    -0.07
    ãģ°
    -0.07
    imon
    -0.07
    ument
    -0.07
    iest
    -0.07
    forth
    -0.07
    que
    -0.07
    POSITIVE LOGITS
    tries
    0.09
    actions
    0.09
    ored
    0.09
    STS
    0.09
     ins
    0.09
    دÙĩ
    0.09
    ented
    0.09
    ãĤ£
    0.09
    athers
    0.09
     resent
    0.09
    Activations Density 0.012%

    No Known Activations