© 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. 5059
    Prev
    Next
    INDEX
    Explanations

    topics and their associated fields or organizations

    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
     Coul
    -0.10
     request
    -0.09
     respectively
    -0.09
     Qi
    -0.09
     Tex
    -0.08
     licence
    -0.08
     selves
    -0.08
     Counter
    -0.08
     Sci
    -0.08
    request
    -0.08
    POSITIVE LOGITS
     absorbing
    0.11
     extinct
    0.10
    elt
    0.09
     Lowell
    0.09
     combos
    0.09
     Eh
    0.09
     assorted
    0.09
     extingu
    0.09
    ISS
    0.09
    layers
    0.09
    Activations Density 0.006%

    No Known Activations