© 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. 47706
    Prev
    Next
    INDEX
    Explanations

    activity or role

    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
     relief
    -0.08
    766
    -0.08
    emp
    -0.08
    elly
    -0.08
     Brennan
    -0.08
     drive
    -0.08
     nth
    -0.08
     adm
    -0.08
     curtain
    -0.08
     driven
    -0.08
    POSITIVE LOGITS
     sport
    0.13
     role
    0.13
     game
    0.13
     prank
    0.11
     instruments
    0.11
    role
    0.10
     games
    0.10
     Zahl
    0.10
     Pipes
    0.10
     videog
    0.10
    Activations Density 0.057%

    No Known Activations