© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15025
    Prev
    Next
    INDEX
    Explanations

    unfolding the present moment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ushi
    -0.09
    otti
    -0.09
    .Video
    -0.09
    ugi
    -0.09
    itant
    -0.08
     PSD
    -0.08
     adel
    -0.08
     Cree
    -0.08
    Explicit
    -0.08
     explicit
    -0.08
    POSITIVE LOGITS
     sensations
    0.21
     moment
    0.16
     sensation
    0.14
     unfolding
    0.14
     Moment
    0.14
     textures
    0.13
     present
    0.12
     whatever
    0.12
     moments
    0.12
     gradual
    0.12
    Activations Density 0.021%

    No Known Activations