© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27793
    Prev
    Next
    INDEX
    Explanations

    attention

    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
    aber
    -0.11
     Encounter
    -0.11
     encountered
    -0.11
     erle
    -0.11
    slick
    -0.10
     Trot
    -0.10
     Abrams
    -0.10
     encounter
    -0.10
     untouched
    -0.10
    LI
    -0.10
    POSITIVE LOGITS
     attention
    0.26
     Attention
    0.22
    attention
    0.19
    Attention
    0.19
     attent
    0.18
     Detail
    0.13
     attn
    0.13
     detail
    0.13
     paid
    0.12
     plight
    0.12
    Activations Density 0.070%

    No Known Activations