© 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. 53794
    Prev
    Next
    INDEX
    Explanations

    names with hyphens and suffixes

    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
    istro
    -0.08
    ãĢĤãĢĮ
    -0.07
     spotted
    -0.06
    alto
    -0.06
    screen
    -0.06
     ðŁĶ
    -0.06
     Twe
    -0.06
     Dirty
    -0.06
     fort
    -0.06
     Mort
    -0.06
    POSITIVE LOGITS
    å½
    0.13
    ULE
    0.13
    erc
    0.11
    .sap
    0.10
    ACP
    0.10
    odu
    0.10
    drawer
    0.10
    ibase
    0.10
    isin
    0.10
    _fname
    0.10
    Activations Density 0.023%

    No Known Activations