© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48580
    Prev
    Next
    INDEX
    Explanations

    enclosed or encapsulated space

    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
     sav
    -0.11
    lings
    -0.10
     Pall
    -0.10
     Slim
    -0.10
    ega
    -0.10
    sav
    -0.10
    tester
    -0.10
    249
    -0.10
     backbone
    -0.09
     Savage
    -0.09
    POSITIVE LOGITS
     enclosed
    0.16
     encaps
    0.15
     enclosure
    0.13
     enclosing
    0.13
    (enc
    0.12
     Enc
    0.11
    enc
    0.11
     area
    0.11
     contained
    0.10
     Sand
    0.10
    Activations Density 0.086%

    No Known Activations