© 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. 48545
    Prev
    Next
    INDEX
    Explanations

    names ending in `reg` followed by `ón`

    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
     provision
    -0.10
    hog
    -0.09
    ocus
    -0.09
    abay
    -0.08
     Gib
    -0.08
     dib
    -0.08
    borg
    -0.08
     Fior
    -0.08
     Uns
    -0.08
     Independence
    -0.08
    POSITIVE LOGITS
     flattened
    0.10
    chts
    0.10
    -alt
    0.10
    scr
    0.10
    quine
    0.10
    ufs
    0.09
     \`
    0.09
     spoiled
    0.09
     trad
    0.09
    OLON
    0.09
    Activations Density 0.123%

    No Known Activations