© 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. 8582
    Prev
    Next
    INDEX
    Explanations

    Names starting with Be

    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
    Not in Any Lists

    No Comments

    Negative Logits
     prick
    -0.09
     Woche
    -0.08
     suff
    -0.08
    oa
    -0.08
    tp
    -0.08
    pf
    -0.08
     thought
    -0.08
    ¼
    -0.07
    ãĤ£
    -0.07
     cam
    -0.07
    POSITIVE LOGITS
     sure
    0.11
     damned
    0.10
    atitude
    0.09
    ornings
    0.09
    stalk
    0.09
    forming
    0.09
    ribbon
    0.09
    atus
    0.09
    umont
    0.09
    nik
    0.09
    Activations Density 0.199%

    No Known Activations