© 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. 4389
    Prev
    Next
    INDEX
    Explanations

    address: location

    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
    cki
    -0.09
    rost
    -0.09
     Welch
    -0.09
    dj
    -0.09
     vers
    -0.09
    okane
    -0.09
     Mueller
    -0.09
    Cond
    -0.08
     entertainment
    -0.08
     strategic
    -0.08
    POSITIVE LOGITS
     exhausted
    0.23
     exhaustion
    0.20
     Exhaust
    0.19
     collapsed
    0.17
     exhausting
    0.16
     limp
    0.16
     breath
    0.16
     recovering
    0.16
     pant
    0.16
     collapse
    0.15
    Activations Density 0.012%

    No Known Activations