© 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. 30385
    Prev
    Next
    INDEX
    Explanations

    "hi" followed by a word part

    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
    ildo
    -0.10
     Brushes
    -0.09
    ento
    -0.09
    ecz
    -0.09
    ous
    -0.09
    auge
    -0.09
    s
    -0.09
    WND
    -0.08
    osity
    -0.08
    andro
    -0.08
    POSITIVE LOGITS
    roy
    0.11
    rog
    0.11
    roi
    0.10
    ATUS
    0.10
    elmet
    0.10
    ROP
    0.09
    imals
    0.09
     widest
    0.09
    annon
    0.09
    anon
    0.09
    Activations Density 0.028%

    No Known Activations