© 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. 47035
    Prev
    Next
    INDEX
    Explanations

    service related roles

    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
     Parkway
    -0.12
     Directors
    -0.11
    izen
    -0.11
    atr
    -0.10
    serv
    -0.10
    ROUGH
    -0.10
    Serv
    -0.10
    inspect
    -0.10
     disen
    -0.10
     Berm
    -0.10
    POSITIVE LOGITS
     booth
    0.15
     helm
    0.13
     shop
    0.13
     till
    0.11
     booths
    0.11
     store
    0.11
     temporarily
    0.10
     hotline
    0.09
     concessions
    0.09
     desk
    0.09
    Activations Density 0.173%

    No Known Activations