© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57417
    Prev
    Next
    INDEX
    Explanations

    approximation or exactness comparison

    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
    rack
    -0.09
     Vine
    -0.09
     dis
    -0.09
     mature
    -0.08
     adultes
    -0.08
     Stack
    -0.08
    Adjacent
    -0.08
    ifecycle
    -0.08
     notebook
    -0.08
    ushman
    -0.08
    POSITIVE LOGITS
     aproxim
    0.11
     slightly
    0.10
     hybrids
    0.10
     approximation
    0.10
     alias
    0.10
     approximately
    0.10
     conver
    0.10
     Hybrid
    0.09
     approx
    0.09
     aprox
    0.09
    Activations Density 0.013%

    No Known Activations