© 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. 773
    Prev
    Next
    INDEX
    Explanations

    metaphorical nouns in context

    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
     ballo
    -0.07
    aco
    -0.07
    cs
    -0.07
    еÑī
    -0.06
     prov
    -0.06
    -origin
    -0.06
     physic
    -0.06
    ubs
    -0.06
    ds
    -0.06
    mits
    -0.06
    POSITIVE LOGITS
     proverb
    0.14
     metaphor
    0.14
    mant
    0.12
    -like
    0.12
     coraz
    0.11
    头
    0.10
     Benz
    0.10
     rond
    0.10
    /sources
    0.10
     antenn
    0.10
    Activations Density 2.077%

    No Known Activations