© 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. 4905
    Prev
    Next
    INDEX
    Explanations

    whether followed by a clause

    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
    sen
    -0.09
    ses
    -0.08
     happen
    -0.08
     behaviour
    -0.07
    chez
    -0.07
    lico
    -0.07
     behavior
    -0.07
     hierarchy
    -0.07
     relations
    -0.07
     circumstance
    -0.07
    POSITIVE LOGITS
    /how
    0.17
    izon
    0.11
    rie
    0.10
    ëıĦ
    0.10
    bee
    0.10
     bast
    0.10
    odel
    0.10
    encion
    0.09
    ие
    0.09
    enal
    0.09
    Activations Density 0.078%

    No Known Activations