© 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. 16575
    Prev
    Next
    INDEX
    Explanations

    la + suffix (e.g., ex, uded, logo)

    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
     barely
    -0.08
    idon
    -0.08
     decid
    -0.08
     bound
    -0.08
     close
    -0.08
     Bau
    -0.07
     sprung
    -0.07
     Kum
    -0.07
     amor
    -0.07
    nox
    -0.07
    POSITIVE LOGITS
    UNCH
    0.13
     cheapest
    0.12
    yz
    0.12
    zym
    0.11
    zar
    0.11
     Reyes
    0.11
    odel
    0.11
    ève
    0.11
    zzle
    0.11
    utenberg
    0.10
    Activations Density 0.010%

    No Known Activations