© 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. 4142
    Prev
    Next
    INDEX
    Explanations

    before followed by an action

    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
     indef
    -0.11
     unfinished
    -0.09
    urd
    -0.09
    olls
    -0.09
     screamed
    -0.09
    oom
    -0.09
    indy
    -0.09
    SEP
    -0.08
     Kov
    -0.08
     unb
    -0.08
    POSITIVE LOGITS
     committing
    0.16
     blindly
    0.14
     emb
    0.14
     beforehand
    0.14
     agreeing
    0.14
     proceeding
    0.14
     undertaking
    0.13
     embark
    0.13
     deciding
    0.13
     commits
    0.12
    Activations Density 0.030%

    No Known Activations