© 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. 56836
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <|endoftext|>
    -0.08
    pond
    -0.07
     Histor
    -0.06
    amic
    -0.06
     *
    -0.06
     blamed
    -0.06
    atra
    -0.06
    ehler
    -0.06
    icularly
    -0.06
     blaming
    -0.06
    POSITIVE LOGITS
    ucer
    0.11
     Womens
    0.11
     Digit
    0.11
    моÑĤ
    0.11
     dere
    0.11
    hof
    0.11
    eref
    0.11
    &m
    0.11
    Ticks
    0.11
    iren
    0.10
    Activations Density 0.000%

    No Known Activations