© 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. 88174
    Prev
    Next
    INDEX
    Explanations

    links or urls

    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
     skim
    -0.09
     Autos
    -0.08
     Independent
    -0.07
     Ner
    -0.07
     autos
    -0.07
     Happ
    -0.07
     dirig
    -0.07
     Ung
    -0.07
     pot
    -0.07
     seeker
    -0.07
    POSITIVE LOGITS
     Link
    0.19
     links
    0.19
     link
    0.19
     Links
    0.18
     chain
    0.18
    .Link
    0.18
    /link
    0.17
    (Link
    0.17
     LINK
    0.17
     Chain
    0.17
    Activations Density 0.141%

    No Known Activations