© 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. 32723
    Prev
    Next
    INDEX
    Explanations

    prepared, ready, or beforehand

    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
     Lars
    -0.09
     bip
    -0.09
    akis
    -0.09
     caster
    -0.09
    assis
    -0.09
    odus
    -0.09
    wich
    -0.09
    verity
    -0.08
    aris
    -0.08
    vie
    -0.08
    POSITIVE LOGITS
     prepared
    0.29
     rehe
    0.29
     beforehand
    0.26
     Prepared
    0.24
    prepared
    0.22
     prepare
    0.22
     ready
    0.20
     prepares
    0.20
     canned
    0.18
     Prepare
    0.18
    Activations Density 0.121%

    No Known Activations