© 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. 46550
    Prev
    Next
    INDEX
    Explanations

    first word or punctuation

    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
     entail
    -0.11
     Carroll
    -0.10
     forfe
    -0.09
     sweeps
    -0.09
     jun
    -0.09
     Preservation
    -0.09
     pud
    -0.09
    -Isl
    -0.09
     combin
    -0.08
     vmax
    -0.08
    POSITIVE LOGITS
     reciprocal
    0.10
     Wilde
    0.10
     Starr
    0.09
     Dane
    0.09
    .python
    0.08
    ignet
    0.08
    ollo
    0.08
    åĨĮ
    0.08
    å½ķ
    0.08
     Py
    0.08
    Activations Density 0.001%

    No Known Activations