© 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. 32650
    Prev
    Next
    INDEX
    Explanations

    pressure versus volume

    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
     pressed
    -0.17
     press
    -0.16
     pressures
    -0.15
     Press
    -0.15
     pressure
    -0.15
     pressing
    -0.14
    Pressed
    -0.14
     presses
    -0.14
     Pressure
    -0.14
    press
    -0.14
    POSITIVE LOGITS
    .HttpServletResponse
    0.08
    .ActionListener
    0.08
    alla
    0.08
    anst
    0.08
    asl
    0.08
     Nord
    0.08
    BX
    0.08
     kc
    0.08
     flakes
    0.08
     bord
    0.08
    Activations Density 0.212%

    No Known Activations