© 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. 4188
    Prev
    Next
    INDEX
    Explanations

    `"`

    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
    .JScrollPane
    -0.13
     Schmidt
    -0.12
     SCH
    -0.12
     Roth
    -0.11
     RTE
    -0.11
    -Sh
    -0.11
     schizophrenia
    -0.11
    SAM
    -0.10
    .Schema
    -0.10
     obed
    -0.10
    POSITIVE LOGITS
     Stein
    0.13
    Ste
    0.12
    .TabIndex
    0.11
     squ
    0.11
     Ste
    0.11
     Stat
    0.10
     Taj
    0.10
    lek
    0.10
     Spi
    0.10
     sper
    0.10
    Activations Density 0.159%

    No Known Activations