© 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. 8919
    Prev
    Next
    INDEX
    Explanations

    quality, mode, scanning, sessions

    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
    oso
    -0.10
     actual
    -0.09
    ÑĤеÑĢ
    -0.09
     itself
    -0.09
     Queens
    -0.09
     literal
    -0.08
     chan
    -0.08
     Undert
    -0.08
    ли
    -0.08
    hydr
    -0.08
    POSITIVE LOGITS
    åĥı
    0.11
     unlike
    0.10
     pes
    0.09
    Unlike
    0.09
    cke
    0.08
    adden
    0.08
     stayed
    0.08
    adas
    0.08
    -*
    0.08
    ith
    0.08
    Activations Density 0.257%

    No Known Activations