© 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. 112893
    Prev
    Next
    INDEX
    Explanations

    relative clauses and conditional statements

    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
    ï¼Īç¬ij
    -0.10
    zs
    -0.09
     massa
    -0.09
    DbContext
    -0.09
    urat
    -0.09
     Ook
    -0.09
    ood
    -0.09
     plein
    -0.09
    NR
    -0.09
    IFn
    -0.09
    POSITIVE LOGITS
    oretical
    0.11
    oret
    0.11
    atos
    0.08
     upon
    0.07
    logan
    0.07
    manuel
    0.07
    cant
    0.07
    usterity
    0.07
    oria
    0.07
    depending
    0.07
    Activations Density 0.216%

    No Known Activations