© 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. 29894
    Prev
    Next
    INDEX
    Explanations

    #include < or <stdbool.h>

    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
     mirrored
    -0.15
     mirrors
    -0.15
     mirror
    -0.14
     Mirror
    -0.13
     reflective
    -0.13
    Mirror
    -0.12
    mirror
    -0.11
     pers
    -0.10
     mir
    -0.09
     Reflex
    -0.09
    POSITIVE LOGITS
     experimented
    0.13
     examining
    0.11
     wig
    0.11
     experimenting
    0.11
     Fare
    0.11
     examined
    0.10
     Experiment
    0.10
     qi
    0.10
     Undo
    0.10
    experiment
    0.10
    Activations Density 0.041%

    No Known Activations