© 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. 14527
    Prev
    Next
    INDEX
    Explanations

    behind

    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
     challenged
    -0.08
     sop
    -0.08
     return
    -0.08
     reciprocal
    -0.08
     crushed
    -0.08
     genes
    -0.08
    ivet
    -0.08
     meeting
    -0.08
     resc
    -0.08
     routine
    -0.08
    POSITIVE LOGITS
     behind
    0.22
     Behind
    0.18
    Behind
    0.17
    beh
    0.14
     draped
    0.12
     rear
    0.11
     joining
    0.11
    joining
    0.11
     posterior
    0.10
     Mell
    0.10
    Activations Density 0.037%

    No Known Activations