© 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. 117183
    Prev
    Next
    INDEX
    Explanations

    let off steam or frustration

    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
     Curt
    -0.09
     shielding
    -0.09
     Curtis
    -0.09
     sco
    -0.09
    arga
    -0.08
     Mandela
    -0.08
    enso
    -0.08
     Summon
    -0.08
    259
    -0.08
     Tut
    -0.08
    POSITIVE LOGITS
     vent
    0.42
     vents
    0.31
     frustrations
    0.31
     outlet
    0.30
     Vent
    0.29
     frustration
    0.27
     pent
    0.26
    vent
    0.25
    Vent
    0.24
     Outlet
    0.24
    Activations Density 0.075%

    No Known Activations