© 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. 28553
    Prev
    Next
    INDEX
    Explanations

    we, they, teams, parties

    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
     together
    -0.25
     Together
    -0.23
    Together
    -0.20
    gether
    -0.14
     Alto
    -0.14
     altogether
    -0.12
     themselves
    -0.11
     tog
    -0.10
     ourselves
    -0.10
     duo
    -0.10
    POSITIVE LOGITS
     both
    0.18
     each
    0.17
    both
    0.16
     BOTH
    0.16
    each
    0.15
     Both
    0.14
    Both
    0.13
    éĥ½
    0.13
     EACH
    0.13
    (each
    0.13
    Activations Density 0.054%

    No Known Activations