© 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. 25955
    Prev
    Next
    INDEX
    Explanations

    saved time and avoided loss

    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
     simul
    -0.10
     detr
    -0.10
     :(
    -0.10
     hind
    -0.10
    /fs
    -0.09
    uf
    -0.09
    dat
    -0.08
     Montgomery
    -0.08
     Hind
    -0.08
     imped
    -0.08
    POSITIVE LOGITS
     potentially
    0.18
     blush
    0.16
     saved
    0.16
     Saved
    0.16
     embarrassment
    0.15
     imminent
    0.15
     possibly
    0.15
    saved
    0.15
     avoided
    0.14
     thanks
    0.14
    Activations Density 0.162%

    No Known Activations