© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115177
    Prev
    Next
    INDEX
    Explanations

    license terms or specifications

    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
     wink
    -0.10
     mirac
    -0.09
    NM
    -0.08
    iola
    -0.08
     trousers
    -0.08
     goose
    -0.08
     nip
    -0.08
     garment
    -0.08
     denim
    -0.08
     peacefully
    -0.08
    POSITIVE LOGITS
     stabil
    0.13
     rider
    0.13
     stabilization
    0.13
     dur
    0.12
     Pell
    0.12
     reassuring
    0.11
     Balt
    0.11
     Rider
    0.11
     gras
    0.11
     throttle
    0.10
    Activations Density 0.027%

    No Known Activations