© 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. 2884
    Prev
    Next
    INDEX
    Explanations

    continue until condition

    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
     exp
    -0.09
     longevity
    -0.08
    ading
    -0.08
    UED
    -0.08
    adar
    -0.08
     gad
    -0.08
    ás
    -0.08
     towards
    -0.08
    ľ
    -0.08
    lav
    -0.08
    POSITIVE LOGITS
     satisfied
    0.13
     enough
    0.13
     exhausted
    0.12
     exhaustion
    0.12
     reached
    0.12
    è¾¾
    0.11
     reaches
    0.11
     desired
    0.11
     reaching
    0.10
     sufficient
    0.10
    Activations Density 0.128%

    No Known Activations