© 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. 4763
    Prev
    Next
    INDEX
    Explanations

    reduced, not, low, rise

    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
    landers
    -0.10
    ANC
    -0.09
    ingleton
    -0.09
     tidy
    -0.08
    OG
    -0.08
    atte
    -0.08
     analy
    -0.08
     Luo
    -0.08
    ont
    -0.08
    ONT
    -0.08
    POSITIVE LOGITS
     less
    0.12
     simultaneous
    0.11
     convers
    0.10
    iris
    0.10
     Fence
    0.10
    egin
    0.10
     fencing
    0.10
     fewer
    0.09
     Aura
    0.09
     minimal
    0.09
    Activations Density 0.431%

    No Known Activations