© 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. 90978
    Prev
    Next
    INDEX
    Explanations

    so [adjective/state]

    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
     receptive
    -0.11
    iac
    -0.10
     recept
    -0.10
    riot
    -0.10
    861
    -0.09
     rounds
    -0.09
    yd
    -0.09
     appart
    -0.09
    erable
    -0.09
    mitt
    -0.09
    POSITIVE LOGITS
    oo
    0.14
    OO
    0.14
    oooo
    0.14
    ooo
    0.13
    oooooooo
    0.12
     clich
    0.12
     gonna
    0.11
    -o
    0.11
     unnecessary
    0.10
     OLD
    0.10
    Activations Density 0.016%

    No Known Activations