© 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. 90089
    Prev
    Next
    INDEX
    Explanations

    since or after a time

    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
    aber
    -0.10
     Maz
    -0.10
    æ±Ł
    -0.09
    azio
    -0.09
    ivo
    -0.09
    AMI
    -0.09
    eron
    -0.09
    eko
    -0.09
    ahan
    -0.09
    CMP
    -0.09
    POSITIVE LOGITS
     initial
    0.10
    264
    0.10
     first
    0.09
    idd
    0.09
    iddy
    0.08
     infamous
    0.08
     Schwe
    0.08
     firstly
    0.08
     pled
    0.08
     ordeal
    0.08
    Activations Density 0.035%

    No Known Activations