© 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. 15329
    Prev
    Next
    INDEX
    Explanations

    jets that 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
     bleed
    -0.14
    ija
    -0.11
    amina
    -0.10
     gaz
    -0.10
     Lair
    -0.10
     bleeding
    -0.10
     squeeze
    -0.10
    iga
    -0.10
     reserve
    -0.10
     unc
    -0.10
    POSITIVE LOGITS
     underside
    0.11
     flows
    0.11
     stream
    0.10
    flows
    0.10
    onto
    0.10
     deflect
    0.10
     originating
    0.10
     downward
    0.10
    _floor
    0.10
     uninterrupted
    0.10
    Activations Density 0.038%

    No Known Activations