© 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. 27363
    Prev
    Next
    INDEX
    Explanations

    surgical reconstruction outcome

    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
    aten
    -0.10
     momentarily
    -0.10
    etting
    -0.09
    omit
    -0.09
    allery
    -0.09
    lements
    -0.09
     immersed
    -0.09
     merits
    -0.09
     éc
    -0.09
     recip
    -0.09
    POSITIVE LOGITS
     reconstructed
    0.19
     permanently
    0.18
     scar
    0.18
     functionality
    0.17
     reconstruction
    0.17
     reconstruct
    0.16
     functional
    0.16
     permanent
    0.16
     restored
    0.16
     scars
    0.15
    Activations Density 0.614%

    No Known Activations