© 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. 8129
    Prev
    Next
    INDEX
    Explanations

    .org URLs

    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
     B
    -0.11
    -B
    -0.11
    'B
    -0.10
    	B
    -0.10
     Bureau
    -0.10
    *B
    -0.09
     BOOL
    -0.09
    _B
    -0.09
     Janeiro
    -0.09
     BCE
    -0.09
    POSITIVE LOGITS
     S
    0.18
    _S
    0.18
    	S
    0.17
    %S
    0.17
    .S
    0.16
    *S
    0.15
    ส
    0.14
    >S
    0.14
    -S
    0.14
     س
    0.14
    Activations Density 1.211%

    No Known Activations