© 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. 89703
    Prev
    Next
    INDEX
    Explanations

    Del followed by names or specific words

    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
    s
    -0.11
    sand
    -0.11
    ello
    -0.10
    san
    -0.09
    swith
    -0.09
    bral
    -0.09
    ellipsis
    -0.09
    ALER
    -0.09
     herein
    -0.09
    ple
    -0.09
    POSITIVE LOGITS
    gado
    0.13
    aney
    0.12
    mol
    0.11
    ivered
    0.10
     Comet
    0.10
     Herm
    0.10
    Led
    0.09
    iece
    0.09
    /comments
    0.09
    clus
    0.09
    Activations Density 0.009%

    No Known Activations