© 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. 8431
    Prev
    Next
    INDEX
    Explanations

    damage and failure

    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
    Not in Any Lists

    No Comments

    Negative Logits
     airflow
    -0.09
     inher
    -0.09
    orama
    -0.08
     endless
    -0.08
    nore
    -0.08
     unrestricted
    -0.08
     endlessly
    -0.08
     embarrass
    -0.07
     hij
    -0.07
     inherit
    -0.07
    POSITIVE LOGITS
     fragile
    0.12
     threshold
    0.12
     Threshold
    0.12
     sensitive
    0.11
     thresholds
    0.11
     delicate
    0.11
     brittle
    0.11
     susceptible
    0.11
     damage
    0.11
     fra
    0.10
    Activations Density 0.517%

    No Known Activations