© 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. 8363
    Prev
    Next
    INDEX
    Explanations

    increase or decrease

    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
     neighb
    -0.10
    iams
    -0.10
    eko
    -0.09
    atus
    -0.09
     preval
    -0.09
    nyder
    -0.09
    лÑİ
    -0.09
    zek
    -0.08
     flap
    -0.08
    .setAuto
    -0.08
    POSITIVE LOGITS
     increases
    0.20
     increase
    0.17
     increased
    0.17
     Increase
    0.17
     increasing
    0.16
     Increases
    0.15
     decreases
    0.15
     Increased
    0.14
    incre
    0.14
    increase
    0.14
    Activations Density 0.266%

    No Known Activations