© 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. 88388
    Prev
    Next
    INDEX
    Explanations

    container parts

    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
     suit
    -0.06
    ogy
    -0.06
    ement
    -0.06
    chemes
    -0.06
     resizable
    -0.06
     Os
    -0.05
     sized
    -0.05
     Mode
    -0.05
     Me
    -0.05
    ings
    -0.05
    POSITIVE LOGITS
    's
    0.23
    ’s
    0.22
     internals
    0.18
     outskirts
    0.18
    `s
    0.17
     interiors
    0.17
    �s
    0.17
    ‘s
    0.17
     corners
    0.17
    ´s
    0.17
    Activations Density 1.442%

    No Known Activations