© 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. 6261
    Prev
    Next
    INDEX
    Explanations

    termination or separation

    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
     harmless
    -0.11
    pel
    -0.11
     eid
    -0.10
     coax
    -0.10
     critically
    -0.10
     impress
    -0.10
     Enc
    -0.10
     safezone
    -0.10
     enc
    -0.10
     pel
    -0.10
    POSITIVE LOGITS
     breakup
    0.19
     abrupt
    0.17
     devastated
    0.14
     painful
    0.14
     freeing
    0.14
     divorce
    0.14
     bitter
    0.13
     devastating
    0.13
     sadness
    0.13
     mutual
    0.13
    Activations Density 0.077%

    No Known Activations