© 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. 61414
    Prev
    Next
    INDEX
    Explanations

    ste words

    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
    ment
    -0.16
    ness
    -0.12
    swith
    -0.11
    ding
    -0.11
    forth
    -0.11
    scene
    -0.11
    igi
    -0.11
    ing
    -0.11
    top
    -0.10
    ary
    -0.10
    POSITIVE LOGITS
    ics
    0.09
    à¹ī
    0.09
    esp
    0.08
    amer
    0.08
    iÄĩ
    0.08
    ates
    0.07
    ers
    0.07
    Ñĩ
    0.07
     recur
    0.07
    Ŀ
    0.07
    Activations Density 0.001%

    No Known Activations