© 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. 90440
    Prev
    Next
    INDEX
    Explanations

    Niagara Falls

    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
     deselect
    -0.11
    hay
    -0.10
     onboard
    -0.10
    allee
    -0.10
     hay
    -0.10
     Cyprus
    -0.10
     MOUSE
    -0.10
     dred
    -0.10
    wolf
    -0.10
     fired
    -0.10
    POSITIVE LOGITS
     waterfall
    0.35
     Falls
    0.25
     casc
    0.25
     cascade
    0.24
     Niagara
    0.23
     falls
    0.22
    falls
    0.21
    cascade
    0.20
     downstream
    0.19
     spray
    0.19
    Activations Density 0.245%

    No Known Activations