© 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. 6823
    Prev
    Next
    INDEX
    Explanations

    types of communication

    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
     crunch
    -0.11
     Newspaper
    -0.11
    mic
    -0.10
     mic
    -0.10
    elm
    -0.10
    -www
    -0.10
     cris
    -0.10
     crisp
    -0.09
    EEP
    -0.09
     Shel
    -0.09
    POSITIVE LOGITS
     Sta
    0.10
     extract
    0.10
     sn
    0.09
     affidavit
    0.09
     sight
    0.09
     together
    0.08
    era
    0.08
     legs
    0.08
    omers
    0.08
     Spike
    0.08
    Activations Density 0.147%

    No Known Activations