© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 30084
    Prev
    Next
    INDEX
    Explanations

    age and approximation

    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
     attention
    -0.12
    itched
    -0.11
    Liked
    -0.11
    attention
    -0.10
    COVID
    -0.10
    uner
    -0.10
     especial
    -0.10
     prenatal
    -0.10
     Attention
    -0.10
     everytime
    -0.10
    POSITIVE LOGITS
     ballpark
    0.10
     Chall
    0.09
     currently
    0.09
     approx
    0.08
     exactly
    0.08
     aproxim
    0.08
     maturity
    0.08
     approximate
    0.08
     Holl
    0.08
    /model
    0.08
    Activations Density 0.017%

    No Known Activations