© 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. 16035
    Prev
    Next
    INDEX
    Explanations

    shed light

    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
    chor
    -0.11
    eut
    -0.10
    agy
    -0.10
    hil
    -0.09
     stump
    -0.09
    dera
    -0.09
    emean
    -0.09
     invent
    -0.09
    reme
    -0.09
     substitution
    -0.09
    POSITIVE LOGITS
     layers
    0.12
     cumbersome
    0.10
     coats
    0.10
     airs
    0.10
     photons
    0.10
     Layers
    0.10
     negativity
    0.10
     garments
    0.09
    /util
    0.09
     responsibilities
    0.09
    Activations Density 0.002%

    No Known Activations