© 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. 5004
    Prev
    Next
    INDEX
    Explanations

    licenses and URLs

    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
     Supplies
    -0.10
    reas
    -0.10
     Nath
    -0.10
    THEN
    -0.09
    IJľ
    -0.09
    го
    -0.09
    akest
    -0.09
    osaic
    -0.09
     Bitte
    -0.09
    ppv
    -0.09
    POSITIVE LOGITS
    rog
    0.08
    ar
    0.08
    ie
    0.08
    ons
    0.08
    as
    0.08
    on
    0.08
     Aber
    0.08
    oxy
    0.08
    eler
    0.08
    <|fim_suffix|>
    0.08
    Activations Density 0.224%

    No Known Activations