© 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. 49221
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initialisms

    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
     japanese
    -0.08
     Ä°
    -0.08
     Gü
    -0.08
     equipments
    -0.08
    EmailAddress
    -0.08
    _information
    -0.08
     Abdel
    -0.08
    morgan
    -0.08
    _dataframe
    -0.08
     hexadecimal
    -0.08
    POSITIVE LOGITS
     meds
    0.23
     biz
    0.23
     reps
    0.20
     docs
    0.20
     regs
    0.20
     info
    0.20
     devs
    0.19
     veggies
    0.17
     Philly
    0.17
     pics
    0.17
    Activations Density 1.210%

    No Known Activations