© 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. 114224
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    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
     foremost
    -0.08
    iesen
    -0.08
     roma
    -0.08
    innen
    -0.08
     yearly
    -0.08
    eties
    -0.08
     Dre
    -0.08
     weekly
    -0.07
    TF
    -0.07
    obre
    -0.07
    POSITIVE LOGITS
    第
    0.28
     第
    0.25
     fifth
    0.25
     sixth
    0.25
     fourth
    0.24
     seventh
    0.22
     Fourth
    0.21
     ninth
    0.20
     eighth
    0.20
     Fifth
    0.20
    Activations Density 1.695%

    No Known Activations