© 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. 46937
    Prev
    Next
    INDEX
    Explanations

    past tense and descriptive endings

    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
    angelo
    -0.10
     Held
    -0.10
     discret
    -0.09
    ipel
    -0.09
     Cousins
    -0.09
     Fountain
    -0.09
    Split
    -0.09
    uli
    -0.09
     Reco
    -0.09
     Shar
    -0.09
    POSITIVE LOGITS
     surfaces
    0.21
     surface
    0.18
     edges
    0.16
    surface
    0.15
     underside
    0.14
     surfaced
    0.13
     sides
    0.12
     inside
    0.12
     Surface
    0.12
     exterior
    0.12
    Activations Density 0.088%

    No Known Activations