© 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. 117201
    Prev
    Next
    INDEX
    Explanations

    internet and networks

    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
     grounded
    -0.07
     safest
    -0.07
     imposs
    -0.07
     Nev
    -0.07
    /by
    -0.07
    air
    -0.06
     anyway
    -0.06
     airport
    -0.06
     safely
    -0.06
     rolling
    -0.06
    POSITIVE LOGITS
    vern
    0.13
    roe
    0.12
    .Directory
    0.12
     Glo
    0.12
     Vern
    0.12
    ).__
    0.11
    bac
    0.11
     publicity
    0.11
    .define
    0.11
    -global
    0.11
    Activations Density 0.001%

    No Known Activations