© 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. 115326
    Prev
    Next
    INDEX
    Explanations

    percentages and comma-separated values

    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
    usu
    -0.11
    ajo
    -0.10
    rist
    -0.10
     Pill
    -0.09
    alfa
    -0.09
     ax
    -0.09
     Fear
    -0.09
     fear
    -0.09
    inq
    -0.09
    Prev
    -0.09
    POSITIVE LOGITS
     arrang
    0.09
    enis
    0.08
    -description
    0.08
     Tate
    0.08
     appro
    0.08
    Decre
    0.08
    plays
    0.08
    unya
    0.08
     dee
    0.07
     Sunshine
    0.07
    Activations Density 0.185%

    No Known Activations