© 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. 53826
    Prev
    Next
    INDEX
    Explanations

    segmentation fault

    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
    ically
    -0.13
    ikal
    -0.11
    ly
    -0.11
    jom
    -0.10
    istic
    -0.09
    ishing
    -0.09
    orgeous
    -0.09
    ishes
    -0.09
    icism
    -0.09
    LEY
    -0.09
    POSITIVE LOGITS
    ations
    0.13
    al
    0.12
    ation
    0.10
    fault
    0.09
    ATION
    0.09
    yt
    0.09
    ments
    0.09
    alem
    0.08
    ures
    0.08
    ative
    0.08
    Activations Density 0.020%

    No Known Activations