© 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. 26411
    Prev
    Next
    INDEX
    Explanations

    rise, back, forward, recovery

    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
     forfe
    -0.10
    iod
    -0.10
     Dome
    -0.10
     Disconnect
    -0.10
    POSE
    -0.10
     disconnect
    -0.10
    -pos
    -0.10
     dims
    -0.10
    disconnect
    -0.09
     dome
    -0.09
    POSITIVE LOGITS
     rebound
    0.15
     greatness
    0.13
     rebuild
    0.13
     rising
    0.12
     emotionally
    0.12
     rises
    0.11
     perse
    0.11
     dragging
    0.11
     soaring
    0.11
     rise
    0.11
    Activations Density 0.043%

    No Known Activations