© 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. 117055
    Prev
    Next
    INDEX
    Explanations

    apparently, so, finally, evidently

    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
     unfortunately
    -0.12
     miracle
    -0.10
     Strange
    -0.10
     alas
    -0.10
     strangely
    -0.10
    amat
    -0.10
     miracles
    -0.10
    iming
    -0.10
    alu
    -0.10
     sadly
    -0.10
    POSITIVE LOGITS
     apparently
    0.18
     so
    0.18
     seemingly
    0.16
     finally
    0.15
    finally
    0.13
     evidently
    0.13
     tão
    0.13
     such
    0.13
     Apparently
    0.12
     Finally
    0.12
    Activations Density 0.072%

    No Known Activations