© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27284
    Prev
    Next
    INDEX
    Explanations

    cumulative calculations or word 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
    tery
    -0.12
    zion
    -0.10
    lights
    -0.10
    ree
    -0.10
    iol
    -0.09
     Secrets
    -0.09
    neh
    -0.09
    uality
    -0.09
    room
    -0.09
    pool
    -0.09
    POSITIVE LOGITS
    ulative
    0.16
    mins
    0.12
    bersome
    0.11
     sum
    0.10
    -sum
    0.10
    iskey
    0.10
     cum
    0.10
     Cum
    0.09
    Cum
    0.09
    obo
    0.09
    Activations Density 0.055%

    No Known Activations