© 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. 61653
    Prev
    Next
    INDEX
    Explanations

    negative calculations

    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
     celebrations
    -0.10
     eup
    -0.10
     celebration
    -0.09
     jub
    -0.09
     trium
    -0.09
     ecstatic
    -0.09
     trivial
    -0.09
     expansion
    -0.09
     augmentation
    -0.09
    akan
    -0.08
    POSITIVE LOGITS
     Negative
    0.22
     negative
    0.22
    Negative
    0.21
    negative
    0.21
     negatively
    0.19
    -negative
    0.18
     negativity
    0.17
     negatives
    0.17
    =-
    0.17
    *(-
    0.16
    Activations Density 0.032%

    No Known Activations