© 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. 113672
    Prev
    Next
    INDEX
    Explanations

    grown up

    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
     historic
    -0.10
    Tomorrow
    -0.09
    historic
    -0.09
     Previous
    -0.08
     Tomorrow
    -0.08
     historical
    -0.08
     previous
    -0.08
    ixon
    -0.08
     Existing
    -0.08
     unlocked
    -0.07
    POSITIVE LOGITS
     grown
    0.29
     mature
    0.25
     evolved
    0.23
     matures
    0.22
     maturity
    0.22
     intervening
    0.21
     growth
    0.21
     changed
    0.20
    grown
    0.20
     grew
    0.18
    Activations Density 0.194%

    No Known Activations