© 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. 31145
    Prev
    Next
    INDEX
    Explanations

    contrast or comparison

    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
     hoping
    -0.10
     unprecedented
    -0.09
     equival
    -0.09
     unexpected
    -0.09
     unusual
    -0.09
     Nolan
    -0.09
     hardest
    -0.09
    zd
    -0.09
    .unique
    -0.09
     incomplete
    -0.09
    POSITIVE LOGITS
     effortlessly
    0.23
     superior
    0.18
     whereas
    0.18
     effortless
    0.18
     fla
    0.16
     Whereas
    0.15
     superiority
    0.15
     meanwhile
    0.14
     unlike
    0.13
     seemingly
    0.13
    Activations Density 0.288%

    No Known Activations