© 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. 30807
    Prev
    Next
    INDEX
    Explanations

    iteration, every, chapter

    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
     Ade
    -0.10
     Bew
    -0.09
    styl
    -0.09
     next
    -0.09
    NSE
    -0.09
    .fun
    -0.08
    xis
    -0.08
    redi
    -0.08
     Mask
    -0.08
    orrent
    -0.08
    POSITIVE LOGITS
     Gabriel
    0.11
     accompanied
    0.11
     further
    0.11
     wors
    0.10
     Gab
    0.10
     felt
    0.10
    inch
    0.10
     corresponds
    0.10
     earns
    0.10
    ats
    0.10
    Activations Density 0.024%

    No Known Activations