© 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. 91303
    Prev
    Next
    INDEX
    Explanations

    riv, river, stream, 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
    aday
    -0.09
    ancel
    -0.08
     Cord
    -0.08
     cord
    -0.08
    igan
    -0.08
    legg
    -0.08
     Plain
    -0.08
    oki
    -0.08
    legen
    -0.08
    viso
    -0.08
    POSITIVE LOGITS
    /stream
    0.15
     flowing
    0.15
     streams
    0.14
     runoff
    0.13
     riv
    0.13
     stream
    0.13
     rivers
    0.12
    -stream
    0.12
     running
    0.12
     flowed
    0.12
    Activations Density 0.007%

    No Known Activations