© 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. 14562
    Prev
    Next
    INDEX
    Explanations

    side related phrases

    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
    istor
    -0.09
    orum
    -0.09
    ist
    -0.09
    agos
    -0.09
    356
    -0.09
    inet
    -0.09
     unnatural
    -0.08
     distur
    -0.08
    sam
    -0.08
    ugo
    -0.08
    POSITIVE LOGITS
     side
    0.21
     Side
    0.19
     SIDE
    0.19
    (side
    0.17
    -side
    0.16
     sid
    0.15
    .Side
    0.15
    Side
    0.15
     sides
    0.15
    side
    0.15
    Activations Density 0.027%

    No Known Activations