© 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. 17956
    Prev
    Next
    INDEX
    Explanations

    placed alongside

    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
    ori
    -0.11
    -begin
    -0.10
    .bd
    -0.10
     Uhr
    -0.09
     bamb
    -0.09
    .hu
    -0.09
    orsi
    -0.09
    736
    -0.09
    itan
    -0.09
     kino
    -0.09
    POSITIVE LOGITS
     alongside
    0.45
     along
    0.36
    along
    0.32
     Along
    0.32
    Along
    0.30
     junto
    0.25
     together
    0.24
    gether
    0.18
    Together
    0.18
     Together
    0.17
    Activations Density 0.456%

    No Known Activations