© 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. 88551
    Prev
    Next
    INDEX
    Explanations

    kinds, ways, forms, reasons

    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
     cour
    -0.13
     airs
    -0.12
     lawy
    -0.11
    DV
    -0.11
    orno
    -0.10
     somehow
    -0.10
     alike
    -0.10
    lemn
    -0.10
    Eric
    -0.10
    kr
    -0.10
    POSITIVE LOGITS
    ef
    0.10
    842
    0.09
    itos
    0.08
    oney
    0.08
     Ket
    0.08
    mand
    0.08
     unint
    0.08
     fung
    0.07
    ave
    0.07
     TBD
    0.07
    Activations Density 0.114%

    No Known Activations