© 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. 4474
    Prev
    Next
    INDEX
    Explanations

    inexplicable situations

    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
     apparently
    -0.18
     evidently
    -0.17
     Apparently
    -0.16
     presumably
    -0.15
     probably
    -0.14
    Apparently
    -0.14
     allegedly
    -0.13
     reportedly
    -0.13
    probably
    -0.11
     Likely
    -0.11
    POSITIVE LOGITS
     Weird
    0.15
     curious
    0.15
     perplex
    0.13
     WTF
    0.13
     curiosity
    0.13
     puzzled
    0.13
    pec
    0.13
     odd
    0.12
     baff
    0.12
     weir
    0.12
    Activations Density 0.077%

    No Known Activations