© 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. 90935
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions

    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
     ctxt
    -0.09
    du
    -0.09
    bir
    -0.09
    603
    -0.08
    udd
    -0.08
    ouv
    -0.08
    irth
    -0.08
     helicopt
    -0.07
    itsu
    -0.07
    ots
    -0.07
    POSITIVE LOGITS
     boy
    0.12
     indeed
    0.12
     rest
    0.12
     rested
    0.12
     Lik
    0.12
     Boy
    0.11
    aggi
    0.11
     Indeed
    0.10
    orney
    0.10
    pects
    0.10
    Activations Density 0.051%

    No Known Activations