© 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. 32662
    Prev
    Next
    INDEX
    Explanations

    plainly obvious why

    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
     unexpected
    -0.13
     surprising
    -0.12
     underestimated
    -0.12
     envisioned
    -0.11
     unfortunately
    -0.11
     Unexpected
    -0.10
     anticipated
    -0.10
     surreal
    -0.10
     unfortunate
    -0.10
    éal
    -0.10
    POSITIVE LOGITS
     clearly
    0.52
     Clearly
    0.41
     obviously
    0.40
    Clearly
    0.36
     plainly
    0.36
     obvious
    0.34
     Obviously
    0.29
     CLEAR
    0.29
     blatantly
    0.28
    Obviously
    0.26
    Activations Density 0.395%

    No Known Activations