© 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. 29008
    Prev
    Next
    INDEX
    Explanations

    volumes, parts, or types with roman numerals

    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
     enough
    -0.10
    conte
    -0.10
     infl
    -0.09
    ptime
    -0.09
    ming
    -0.09
    anging
    -0.09
    YES
    -0.09
    curring
    -0.09
    CRT
    -0.09
    ging
    -0.09
    POSITIVE LOGITS
     II
    0.21
     III
    0.16
    -II
    0.14
     ii
    0.14
    II
    0.12
     edition
    0.12
    1
    0.10
     IV
    0.10
    2
    0.10
    III
    0.10
    Activations Density 0.219%

    No Known Activations