© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89947
    Prev
    Next
    INDEX
    Explanations

    delivery locations

    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
     Micha
    -0.10
     Temper
    -0.09
     Chunk
    -0.09
    GW
    -0.09
    897
    -0.09
     twitch
    -0.09
     Twitch
    -0.09
     fart
    -0.09
    PLAN
    -0.09
    -pre
    -0.09
    POSITIVE LOGITS
     doorstep
    0.31
     mailbox
    0.26
     door
    0.24
     altar
    0.19
     doors
    0.18
    door
    0.18
    -door
    0.17
     Door
    0.17
     inbox
    0.17
     desks
    0.17
    Activations Density 0.150%

    No Known Activations