© 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. 56395
    Prev
    Next
    INDEX
    Explanations

    word fragments or beginning fragments

    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
    fried
    -0.09
    Nu
    -0.09
    ulumi
    -0.08
    aments
    -0.08
     charts
    -0.08
    onet
    -0.08
    iaux
    -0.07
    yw
    -0.07
    ppe
    -0.07
     Ellis
    -0.07
    POSITIVE LOGITS
    der
    0.09
     Bhar
    0.09
    ä¿
    0.08
     Bose
    0.08
     warrant
    0.08
    ith
    0.08
     Morm
    0.08
    Multiplicity
    0.08
    rac
    0.08
    inos
    0.08
    Activations Density 0.002%

    No Known Activations