© 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. 16460
    Prev
    Next
    INDEX
    Explanations

    industries and services

    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
    .,
    -0.12
    unused
    -0.10
    ived
    -0.09
    erval
    -0.09
    ugu
    -0.09
     sez
    -0.09
     frame
    -0.08
     Dup
    -0.08
     reality
    -0.08
    omer
    -0.08
    POSITIVE LOGITS
    !.
    0.10
    _.
    0.10
    /browse
    0.10
    itra
    0.10
     {}.
    0.10
    umo
    0.10
    __.
    0.09
    ocket
    0.09
    ++.
    0.09
     .
    0.09
    Activations Density 0.170%

    No Known Activations