© 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. 29768
    Prev
    Next
    INDEX
    Explanations

    reaching limits

    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
     Andr
    -0.08
     Roz
    -0.08
     underst
    -0.08
     distur
    -0.08
    âĨĵ
    -0.08
    apat
    -0.08
     vant
    -0.08
     CLEAR
    -0.07
    isser
    -0.07
     unfamiliar
    -0.07
    POSITIVE LOGITS
     plateau
    0.35
     satur
    0.30
     saturated
    0.28
     saturation
    0.28
     stops
    0.26
     limit
    0.26
     reached
    0.25
     stopped
    0.25
     stop
    0.25
     stagn
    0.25
    Activations Density 0.841%

    No Known Activations