© 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. 91522
    Prev
    Next
    INDEX
    Explanations

    data available and files

    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
     darkest
    -0.08
    ]+)/
    -0.08
     unint
    -0.08
    dense
    -0.08
     cater
    -0.08
     Dante
    -0.08
    ilent
    -0.08
     waters
    -0.08
    icl
    -0.07
    onet
    -0.07
    POSITIVE LOGITS
     newData
    0.21
    (Data
    0.19
    .Data
    0.18
     setData
    0.17
     Data
    0.17
    >Data
    0.17
    /Data
    0.17
     getData
    0.16
    IData
    0.16
    =data
    0.15
    Activations Density 1.289%

    No Known Activations