© 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. 48859
    Prev
    Next
    INDEX
    Explanations

    is permitted and is governed

    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
     scraped
    -0.11
    NoSuch
    -0.10
     lassen
    -0.10
    ENTE
    -0.10
    stamp
    -0.10
     Hav
    -0.10
    ça
    -0.10
    entine
    -0.10
     diced
    -0.10
     Brid
    -0.10
    POSITIVE LOGITS
     encouraged
    0.17
     desirable
    0.15
     expected
    0.13
     necessary
    0.12
     welcomed
    0.12
     desired
    0.11
     desire
    0.11
     advisable
    0.11
     appreciated
    0.11
     inevitable
    0.11
    Activations Density 0.234%

    No Known Activations