© 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. 49004
    Prev
    Next
    INDEX
    Explanations

    change over time

    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
     Nab
    -0.11
     doomed
    -0.11
    817
    -0.10
    ifr
    -0.09
     disappear
    -0.09
    wipe
    -0.09
    aba
    -0.09
    ator
    -0.09
     hindsight
    -0.09
    alg
    -0.09
    POSITIVE LOGITS
     considerably
    0.19
     since
    0.18
     greatly
    0.17
     significantly
    0.17
     tremendously
    0.16
     over
    0.16
     overtime
    0.16
     vastly
    0.15
     immensely
    0.15
     markedly
    0.14
    Activations Density 0.118%

    No Known Activations