© 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. 57635
    Prev
    Next
    INDEX
    Explanations

    look at

    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
    ereo
    -0.10
     Guest
    -0.09
     Couple
    -0.09
    aqu
    -0.08
     hizo
    -0.08
    ennie
    -0.08
    adows
    -0.08
    LOCKS
    -0.07
     Perspective
    -0.07
    leep
    -0.07
    POSITIVE LOGITS
    abh
    0.10
     most
    0.09
     abduction
    0.09
    Ps
    0.09
     '_',
    0.09
     sequentially
    0.08
     distant
    0.08
    {name
    0.08
    GW
    0.08
     Zuk
    0.08
    Activations Density 0.028%

    No Known Activations