© 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. 676
    Prev
    Next
    INDEX
    Explanations

    names and descriptions

    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
     similar
    -0.12
     certain
    -0.12
     the
    -0.09
     enough
    -0.09
    atism
    -0.09
    ophobia
    -0.09
    ivism
    -0.09
     a
    -0.09
    anism
    -0.08
    oleon
    -0.08
    POSITIVE LOGITS
     portion
    0.16
     aforementioned
    0.15
    osphere
    0.15
     workings
    0.13
     confines
    0.13
    etherlands
    0.13
    iest
    0.13
     nature
    0.13
    niest
    0.12
     entirety
    0.12
    Activations Density 4.378%

    No Known Activations