© 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. 47136
    Prev
    Next
    INDEX
    Explanations

    observation and clear states

    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
     resulting
    -0.10
     bev
    -0.09
     resultant
    -0.09
     upro
    -0.09
     Cle
    -0.09
    atin
    -0.09
     cheered
    -0.09
    ix
    -0.09
    irit
    -0.08
     mend
    -0.08
    POSITIVE LOGITS
     clearly
    0.26
     evidently
    0.25
     Clearly
    0.24
    Clearly
    0.23
     obviously
    0.23
     apparently
    0.16
     Obviously
    0.16
     Apparently
    0.15
    Obviously
    0.14
     unmistak
    0.14
    Activations Density 0.012%

    No Known Activations