© 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. 88261
    Prev
    Next
    INDEX
    Explanations

    correlated with

    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
     Garland
    -0.11
     elaborate
    -0.11
     Klopp
    -0.11
     interchange
    -0.11
     dope
    -0.10
    gens
    -0.10
     intervene
    -0.10
     Gunn
    -0.10
     veto
    -0.10
     Congress
    -0.10
    POSITIVE LOGITS
     correlation
    0.24
     correlated
    0.21
     correlations
    0.20
     correlate
    0.20
     correl
    0.18
     correlates
    0.18
     Cor
    0.16
     positively
    0.14
    -cor
    0.14
    /ca
    0.12
    Activations Density 0.385%

    No Known Activations