© 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. 1450
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    ala
    -0.07
     Eisen
    -0.07
     declared
    -0.07
    ymoon
    -0.06
    Parm
    -0.06
    attr
    -0.06
    lä
    -0.06
     param
    -0.06
    outh
    -0.06
     description
    -0.06
    POSITIVE LOGITS
     characters
    0.12
    符
    0.12
    -del
    0.11
    åŃĹ符
    0.11
    åı·
    0.11
    Colon
    0.10
     preceded
    0.10
     del
    0.10
     delimiter
    0.10
     sign
    0.10
    Activations Density 1.292%

    No Known Activations