© 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. 61331
    Prev
    Next
    INDEX
    Explanations

    physiological and pathological conditions

    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
    ÑģÑı
    -0.10
    tract
    -0.09
    liness
    -0.09
    .GroupLayout
    -0.09
    lie
    -0.08
    enes
    -0.08
    ly
    -0.08
    utable
    -0.08
    lad
    -0.08
     deg
    -0.08
    POSITIVE LOGITS
    orts
    0.09
    ë§
    0.09
     compt
    0.08
     Telecom
    0.08
     Mur
    0.08
     wr
    0.08
    ing
    0.08
    es
    0.08
    computer
    0.08
     Trem
    0.07
    Activations Density 0.012%

    No Known Activations