© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26974
    Prev
    Next
    INDEX
    Explanations

    online or offline resources

    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
    blend
    -0.09
     Blend
    -0.09
     blend
    -0.09
    ric
    -0.08
     COMP
    -0.08
    lio
    -0.07
     gall
    -0.07
     Sor
    -0.07
     Sind
    -0.07
    asca
    -0.07
    POSITIVE LOGITS
     offline
    0.12
     Offline
    0.12
     jun
    0.11
    okus
    0.11
     circuit
    0.10
     Kerr
    0.10
    /frontend
    0.10
    atron
    0.10
     closure
    0.10
    entropy
    0.10
    Activations Density 0.004%

    No Known Activations