© 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. 5698
    Prev
    Next
    INDEX
    Explanations

    way

    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
     Emm
    -0.10
    andel
    -0.10
    NCY
    -0.10
     cof
    -0.09
     Bil
    -0.09
     Li
    -0.09
    Li
    -0.09
     massa
    -0.09
     Ny
    -0.09
    anas
    -0.09
    POSITIVE LOGITS
     whisk
    0.09
    StackSize
    0.09
     eff
    0.09
    pers
    0.09
     impl
    0.08
     Åĵ
    0.08
    esa
    0.08
    AMI
    0.08
     ratt
    0.08
     hatch
    0.07
    Activations Density 0.459%

    No Known Activations