© 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. 91568
    Prev
    Next
    INDEX
    Explanations

    connector for clauses or phrases

    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
     breakup
    -0.08
    {},
    -0.08
    ctr
    -0.08
     Kramer
    -0.08
    enet
    -0.08
    iled
    -0.08
     populous
    -0.07
     invokes
    -0.07
    ce
    -0.07
    979
    -0.07
    POSITIVE LOGITS
     alike
    0.11
    asan
    0.11
    apon
    0.10
     piv
    0.10
     fas
    0.10
    hee
    0.09
     disproportion
    0.09
    Las
    0.09
     Dé
    0.09
     goog
    0.09
    Activations Density 0.011%

    No Known Activations