© 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. 29928
    Prev
    Next
    INDEX
    Explanations

    I am / I'm glad/sorry/doing

    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
     eg
    -0.11
     Eg
    -0.10
     Duo
    -0.09
     Gren
    -0.09
     Reputation
    -0.09
     imperson
    -0.09
    wipe
    -0.09
     ego
    -0.09
     arrived
    -0.09
     severed
    -0.09
    POSITIVE LOGITS
     sorry
    0.13
     glad
    0.11
    orte
    0.10
     actually
    0.10
     kinda
    0.10
    sorry
    0.10
     Sorry
    0.10
    jom
    0.09
     imagin
    0.09
    hosts
    0.09
    Activations Density 0.049%

    No Known Activations