© 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. 16976
    Prev
    Next
    INDEX
    Explanations

    seat selection, assemblies, belts

    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
    uder
    -0.11
    vard
    -0.11
    cer
    -0.10
    cers
    -0.10
    lexical
    -0.10
    itore
    -0.10
    èle
    -0.10
    icles
    -0.10
    TZ
    -0.09
    cola
    -0.09
    POSITIVE LOGITS
    belt
    0.15
    ings
    0.14
    mate
    0.11
    mates
    0.11
    atable
    0.11
     recl
    0.10
    lift
    0.10
     uphol
    0.10
    manship
    0.10
    less
    0.10
    Activations Density 0.027%

    No Known Activations