© 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. 30791
    Prev
    Next
    INDEX
    Explanations

    license or copyright notice

    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
     tear
    -0.10
    stub
    -0.10
    Gram
    -0.10
    entic
    -0.09
    gram
    -0.09
     Gram
    -0.09
    context
    -0.09
     Stadium
    -0.09
    uby
    -0.09
    apse
    -0.09
    POSITIVE LOGITS
     Orr
    0.09
     exp
    0.08
     arom
    0.08
     datum
    0.08
    pus
    0.08
    cis
    0.08
    cq
    0.08
     scoped
    0.08
     vit
    0.08
     Lone
    0.08
    Activations Density 0.001%

    No Known Activations