© 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. 91872
    Prev
    Next
    INDEX
    Explanations

    lost or losing

    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
     losses
    -0.12
     Lost
    -0.12
     lost
    -0.11
    lost
    -0.11
    -loss
    -0.10
     Loss
    -0.10
     extensively
    -0.10
    Lost
    -0.10
     holding
    -0.10
     Jennings
    -0.10
    POSITIVE LOGITS
     forever
    0.19
     Forever
    0.15
     permanently
    0.12
    Forever
    0.12
     Beard
    0.10
     trag
    0.09
    åĪ°
    0.09
     permanent
    0.09
     virgin
    0.09
     unrest
    0.09
    Activations Density 0.036%

    No Known Activations