© 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. 58695
    Prev
    Next
    INDEX
    Explanations

    can cause or lead to problems

    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
    å¤Ħ
    -0.11
     inex
    -0.11
    awah
    -0.10
    atrix
    -0.10
    ORG
    -0.09
     perish
    -0.08
     morally
    -0.08
     Morrow
    -0.08
     corr
    -0.08
     vacc
    -0.08
    POSITIVE LOGITS
    .Hidden
    0.10
    uv
    0.09
    بر
    0.09
    ithe
    0.09
    ëĤĺ
    0.09
     makeshift
    0.08
     Rin
    0.08
     Spi
    0.08
     Oriental
    0.08
    pee
    0.08
    Activations Density 0.065%

    No Known Activations