© 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. 58291
    Prev
    Next
    INDEX
    Explanations

    source code

    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
     Inflate
    -0.07
    lain
    -0.07
     McB
    -0.07
     Michel
    -0.07
    /rec
    -0.07
     Brennan
    -0.07
    references
    -0.07
     Bet
    -0.07
    avis
    -0.06
    ħ§
    -0.06
    POSITIVE LOGITS
     buck
    0.10
    share
    0.10
    eton
    0.09
    roids
    0.09
    agen
    0.09
     swallow
    0.09
    egen
    0.09
    ippi
    0.09
    vic
    0.09
     Rog
    0.09
    Activations Density 0.004%

    No Known Activations