© 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. 14702
    Prev
    Next
    INDEX
    Explanations

    not many, and proud of it

    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
     OMG
    -0.10
    lek
    -0.09
    ajar
    -0.09
     posting
    -0.09
     realmente
    -0.09
    posted
    -0.09
    hoe
    -0.09
     ie
    -0.09
     Definitely
    -0.09
     Unsure
    -0.09
    POSITIVE LOGITS
     somebody
    0.13
     anybody
    0.12
     everybody
    0.12
     Mash
    0.10
     explic
    0.10
     Everybody
    0.10
     fucking
    0.10
     ({
    0.10
    Everybody
    0.10
     famously
    0.10
    Activations Density 0.229%

    No Known Activations