© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48706
    Prev
    Next
    INDEX
    Explanations

    past / previous relationships

    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
     tightening
    -0.09
    ENO
    -0.09
     injustice
    -0.09
     complain
    -0.09
     reflect
    -0.09
     boredom
    -0.09
     abusing
    -0.09
     choke
    -0.09
     morale
    -0.09
    âķ
    -0.08
    POSITIVE LOGITS
     past
    0.25
     Past
    0.22
    past
    0.21
     baggage
    0.20
     previous
    0.20
    Past
    0.19
     Previous
    0.19
    previous
    0.18
    _past
    0.17
    Previous
    0.17
    Activations Density 0.044%

    No Known Activations