© 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. 29162
    Prev
    Next
    INDEX
    Explanations

    subjects drank a meal

    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
     Rodrigo
    -0.10
     mutable
    -0.10
    uit
    -0.10
    asso
    -0.09
    joint
    -0.09
     Somehow
    -0.09
    arna
    -0.09
     hobby
    -0.09
     coincidence
    -0.09
     AMS
    -0.09
    POSITIVE LOGITS
     stimuli
    0.19
     standardized
    0.18
     simulated
    0.17
     stimulus
    0.16
     randomly
    0.14
     sham
    0.14
     neutral
    0.14
     randomized
    0.13
     researcher
    0.13
     dummy
    0.13
    Activations Density 3.350%

    No Known Activations