© 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. 61185
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     Preston
    -0.11
    ookie
    -0.10
     Lod
    -0.09
     Says
    -0.09
    awah
    -0.09
     Dez
    -0.09
    undi
    -0.08
    ardo
    -0.08
     jour
    -0.08
    awe
    -0.08
    POSITIVE LOGITS
    ELL
    0.09
    ufe
    0.09
    adera
    0.09
    ridge
    0.08
    zm
    0.08
    oven
    0.08
    Refer
    0.08
    combe
    0.08
    662
    0.08
     Refer
    0.08
    Activations Density 0.012%

    No Known Activations