© 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. 49233
    Prev
    Next
    INDEX
    Explanations

    apart, aside, forth, sights

    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
    jur
    -0.08
     unf
    -0.08
    utes
    -0.08
     thoroughly
    -0.08
    ivy
    -0.08
     Snapshot
    -0.08
     Moms
    -0.08
    asan
    -0.08
     anch
    -0.08
    odo
    -0.07
    POSITIVE LOGITS
     aside
    0.22
     abl
    0.17
     apart
    0.17
     Aside
    0.16
    tle
    0.15
     forth
    0.15
     afl
    0.15
     sights
    0.15
    aside
    0.14
     tone
    0.14
    Activations Density 0.369%

    No Known Activations