© 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. 89609
    Prev
    Next
    INDEX
    Explanations

    the top tier/level/currency/award

    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
    -keys
    -0.11
    sto
    -0.11
     Germans
    -0.11
     aer
    -0.10
    erno
    -0.10
     Mich
    -0.10
     Worm
    -0.10
    Wr
    -0.10
    essler
    -0.10
    toolbox
    -0.10
    POSITIVE LOGITS
    IFA
    0.08
     Kont
    0.08
     Crane
    0.08
     crane
    0.07
     kab
    0.07
    ora
    0.07
    awan
    0.07
     Nagar
    0.07
     managing
    0.07
     incons
    0.07
    Activations Density 0.002%

    No Known Activations