© 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. 50125
    Prev
    Next
    INDEX
    Explanations

    . or on or by followed by proper noun or date

    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
    oui
    -0.10
    мен
    -0.10
    vor
    -0.10
     Dix
    -0.09
     satisfaction
    -0.09
    keh
    -0.09
    Greek
    -0.09
     Greek
    -0.09
    ownt
    -0.09
    quote
    -0.09
    POSITIVE LOGITS
     Mash
    0.21
     mash
    0.12
    Https
    0.12
     pcm
    0.10
     livest
    0.10
     depress
    0.10
    WATCH
    0.09
    pcs
    0.09
    Upload
    0.09
    (op
    0.09
    Activations Density 0.094%

    No Known Activations