© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56953
    Prev
    Next
    INDEX
    Explanations

    because it's

    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
    umps
    -0.08
     knocking
    -0.08
    wipe
    -0.08
    Ü
    -0.08
     pou
    -0.08
    pat
    -0.07
    urred
    -0.07
    ewan
    -0.07
     Rising
    -0.07
     platforms
    -0.07
    POSITIVE LOGITS
     influence
    0.10
     Influence
    0.10
     underlying
    0.09
    äs
    0.09
     optimization
    0.09
     optim
    0.09
     intentionally
    0.09
     compens
    0.09
    ock
    0.08
    oshi
    0.08
    Activations Density 0.109%

    No Known Activations