© 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. 116577
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Hein
    -0.10
     vin
    -0.10
    Labour
    -0.10
     ach
    -0.10
     SCAN
    -0.10
     Jerusalem
    -0.10
     Rounds
    -0.10
    ipt
    -0.10
     tand
    -0.09
    oulder
    -0.09
    POSITIVE LOGITS
     Standards
    0.09
    ims
    0.09
     Mou
    0.09
    848
    0.09
    -vs
    0.08
     Daly
    0.08
    iani
    0.08
     drib
    0.08
    .Bounds
    0.08
     fancy
    0.08
    Activations Density 0.000%

    No Known Activations