© 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. 15589
    Prev
    Next
    INDEX
    Explanations

    we are, we provide, we understand

    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
    uta
    -0.11
    tape
    -0.09
    ropa
    -0.08
    achie
    -0.08
     charity
    -0.08
     Spec
    -0.08
    spec
    -0.08
    мож
    -0.08
     Nexus
    -0.08
     dob
    -0.08
    POSITIVE LOGITS
     understands
    0.27
     recognizes
    0.26
     understand
    0.25
     believes
    0.25
     realizes
    0.24
     recognizing
    0.24
     realizing
    0.24
     realized
    0.23
     believe
    0.23
     understanding
    0.23
    Activations Density 0.181%

    No Known Activations