© 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. 58822
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or unfortunate outcomes

    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
    rompt
    -0.09
    obi
    -0.09
     polarization
    -0.08
    icket
    -0.08
     Durham
    -0.08
     penetrated
    -0.08
     OPEN
    -0.08
     Polar
    -0.08
     projected
    -0.08
     bas
    -0.08
    POSITIVE LOGITS
    (typ
    0.10
     unfair
    0.10
     cursed
    0.09
     Cobb
    0.09
     perverse
    0.09
    ")));
    0.09
     Ley
    0.09
     unlucky
    0.09
     mocking
    0.09
     vest
    0.08
    Activations Density 0.065%

    No Known Activations