© 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. 28742
    Prev
    Next
    INDEX
    Explanations

    offline and physical

    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
     bör
    -0.09
     unb
    -0.09
    inas
    -0.08
    elf
    -0.08
    åĥ
    -0.08
    Unt
    -0.08
    ingers
    -0.08
    inger
    -0.08
    ноп
    -0.08
     crem
    -0.08
    POSITIVE LOGITS
     offline
    0.53
     Offline
    0.47
    offline
    0.40
     physical
    0.40
    Offline
    0.40
     physically
    0.34
     Physical
    0.33
    physical
    0.32
    Physical
    0.30
     brick
    0.29
    Activations Density 0.737%

    No Known Activations