© 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. 58960
    Prev
    Next
    INDEX
    Explanations

    file paths and user directories

    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
    orial
    -0.08
    pler
    -0.08
     hin
    -0.08
    tesy
    -0.07
     "\↵
    -0.07
     *_
    -0.07
     Traditional
    -0.07
     fon
    -0.07
    cast
    -0.07
    chan
    -0.07
    POSITIVE LOGITS
    Ñĥж
    0.11
     wired
    0.09
     Vul
    0.09
    kart
    0.08
    ibles
    0.08
     Tale
    0.08
    èī
    0.08
     Fam
    0.08
    -background
    0.08
     Lif
    0.08
    Activations Density 0.001%

    No Known Activations