© 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. 113119
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
     Mitar
    -0.08
    <|fim_middle|>
    -0.07
    IJ
    -0.07
     physic
    -0.07
    -instance
    -0.07
     feas
    -0.07
     Executors
    -0.07
    phalt
    -0.07
     mortal
    -0.07
     fur
    -0.06
    POSITIVE LOGITS
     also
    0.19
    also
    0.17
     began
    0.17
     has
    0.15
     was
    0.15
     meanwhile
    0.14
     had
    0.14
     (/
    0.14
     is
    0.13
     vs
    0.13
    Activations Density 1.156%

    No Known Activations