© 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. 58449
    Prev
    Next
    INDEX
    Explanations

    firing shots

    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
    earn
    -0.09
     alive
    -0.09
    alive
    -0.09
     nearer
    -0.08
    _alive
    -0.08
    Alive
    -0.08
    ors
    -0.07
    ted
    -0.07
    aire
    -0.07
    odem
    -0.07
    POSITIVE LOGITS
     Away
    0.10
    imum
    0.10
    ularity
    0.09
    Away
    0.09
    uspend
    0.09
     âĢİ
    0.09
     Ree
    0.09
     Towards
    0.09
    uff
    0.09
    ات
    0.09
    Activations Density 0.006%

    No Known Activations