© 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. 400
    Prev
    Next
    INDEX
    Explanations

    increase in

    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
    igh
    -0.10
     reversible
    -0.10
    heed
    -0.09
    IAS
    -0.09
    iev
    -0.09
     completely
    -0.09
    zas
    -0.09
     reversal
    -0.08
    ria
    -0.08
    izzard
    -0.08
    POSITIVE LOGITS
    /de
    0.23
    /im
    0.15
    /change
    0.13
    /rem
    0.13
    /en
    0.12
     exponentially
    0.12
    /add
    0.11
     chances
    0.11
    /pre
    0.10
    /prom
    0.10
    Activations Density 1.386%

    No Known Activations