© 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. 61304
    Prev
    Next
    INDEX
    Explanations

    numeric sequences

    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
    Negative Logits
    /mit
    -0.11
     fils
    -0.10
    ixo
    -0.10
    ymb
    -0.10
    errick
    -0.10
    xed
    -0.10
     Crafts
    -0.10
    igel
    -0.10
    !↵↵↵↵
    -0.10
    UTE
    -0.10
    POSITIVE LOGITS
     Barr
    0.09
     recurs
    0.08
     occasional
    0.06
    iks
    0.06
     Pap
    0.06
     opportun
    0.06
     bumper
    0.06
     barr
    0.06
     br
    0.06
     Match
    0.06
    Activations Density 0.018%

    No Known Activations