© 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. 1997
    Prev
    Next
    INDEX
    Explanations

    based on pattern or hypothesis

    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
    coder
    -0.08
     departing
    -0.08
    lobe
    -0.08
    /validation
    -0.08
    weise
    -0.08
    tones
    -0.08
    adies
    -0.07
     BaÅŁ
    -0.07
     repeating
    -0.07
    alli
    -0.07
    POSITIVE LOGITS
    -based
    0.16
     management
    0.14
    wise
    0.14
    -centric
    0.14
    -wise
    0.13
     analysis
    0.13
    -focused
    0.13
    (s
    0.13
    sWith
    0.12
    -related
    0.12
    Activations Density 4.043%

    No Known Activations