© 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. 15361
    Prev
    Next
    INDEX
    Explanations

    review status

    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
    unya
    -0.10
     Ley
    -0.09
     dram
    -0.09
    arro
    -0.09
    kart
    -0.08
     Curtain
    -0.08
     Hue
    -0.08
    apon
    -0.08
    owell
    -0.08
    ernet
    -0.08
    POSITIVE LOGITS
     pending
    0.13
     kindness
    0.10
     Pending
    0.10
    bum
    0.09
     bum
    0.09
     posterior
    0.09
    ¦
    0.09
    ha
    0.09
    pending
    0.09
    aje
    0.09
    Activations Density 0.001%

    No Known Activations