© 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. 56604
    Prev
    Next
    INDEX
    Explanations

    I will be, in light, which it, Mike Pompeo will, Now I, do a

    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
     Novel
    -0.08
    366
    -0.08
     handful
    -0.08
    .And
    -0.08
     sou
    -0.08
    yers
    -0.08
     blunt
    -0.08
     reviewer
    -0.08
    CAT
    -0.08
    ilor
    -0.08
    POSITIVE LOGITS
    ’h
    0.10
     extremely
    0.09
     (“
    0.09
     originates
    0.09
     agre
    0.09
     voy
    0.08
     Lon
    0.08
     incl
    0.08
    quete
    0.08
     VERY
    0.08
    Activations Density 0.021%

    No Known Activations