© 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. 27039
    Prev
    Next
    INDEX
    Explanations

    finished, residue, excess

    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
     disag
    -0.11
     dissect
    -0.10
     Pall
    -0.09
    oric
    -0.09
     ferr
    -0.09
    747
    -0.08
     Kont
    -0.08
     ber
    -0.08
     Sag
    -0.08
     inhab
    -0.08
    POSITIVE LOGITS
     excess
    0.14
     finished
    0.12
     residue
    0.12
     Finished
    0.11
    Finished
    0.11
     residual
    0.11
     excessive
    0.10
     final
    0.10
    finished
    0.10
    -example
    0.10
    Activations Density 0.016%

    No Known Activations