© 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. 28589
    Prev
    Next
    INDEX
    Explanations

    river flow

    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
     Vent
    -0.11
     shaken
    -0.09
     alo
    -0.09
     rings
    -0.09
     refund
    -0.09
     vent
    -0.09
     capit
    -0.09
     Brewer
    -0.08
     Pall
    -0.08
     dom
    -0.08
    POSITIVE LOGITS
     flowing
    0.34
     flows
    0.31
     flow
    0.29
     flowed
    0.28
    flow
    0.27
    flows
    0.26
     Flow
    0.25
    æµģ
    0.25
    -flow
    0.24
    Flow
    0.24
    Activations Density 0.415%

    No Known Activations