© 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. 7097
    Prev
    Next
    INDEX
    Explanations

    U.S. Court

    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
     specialised
    -0.09
     saints
    -0.09
     Blond
    -0.09
    brown
    -0.09
    itra
    -0.09
    mbH
    -0.09
    ieres
    -0.09
     calle
    -0.09
     organised
    -0.09
    ÂĢÂ
    -0.09
    POSITIVE LOGITS
     Department
    0.13
     Dept
    0.13
     dept
    0.12
     postal
    0.10
     Meadows
    0.09
    iti
    0.09
     Abdel
    0.09
     Paulo
    0.09
     backing
    0.09
     Census
    0.09
    Activations Density 0.227%

    No Known Activations