© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4743
    Prev
    Next
    INDEX
    Explanations

    reflection or echoes

    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
     automatically
    -0.08
     dow
    -0.07
     con
    -0.07
     Wil
    -0.07
     Burst
    -0.07
     Diss
    -0.06
     isolated
    -0.06
     invert
    -0.06
     consum
    -0.06
     inert
    -0.06
    POSITIVE LOGITS
     rico
    0.15
     reflections
    0.14
     Reflection
    0.14
     bounced
    0.13
     specular
    0.13
    Reflection
    0.13
    ¡°
    0.13
     travelling
    0.12
     lens
    0.12
    ĶåĽŀ
    0.12
    Activations Density 0.149%

    No Known Activations