© 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. 3946
    Prev
    Next
    INDEX
    Explanations

    Danish or American

    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
     forthcoming
    -0.10
     ack
    -0.09
    :*
    -0.09
     understandably
    -0.09
     backers
    -0.09
     therein
    -0.09
     Hicks
    -0.08
    *.
    -0.08
     —
    -0.08
    xcf
    -0.08
    POSITIVE LOGITS
     ones
    0.10
     Ones
    0.10
    ág
    0.10
     suburb
    0.10
    icy
    0.09
     collabor
    0.09
    Donate
    0.08
    onest
    0.08
    ologist
    0.08
    grams
    0.08
    Activations Density 0.006%

    No Known Activations