© 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. 113943
    Prev
    Next
    INDEX
    Explanations

    worked as

    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
    unge
    -0.13
    WORK
    -0.11
    ìĨ
    -0.11
    olas
    -0.11
    _mas
    -0.11
    endon
    -0.10
     imminent
    -0.10
    isson
    -0.10
     Working
    -0.10
     workload
    -0.10
    POSITIVE LOGITS
     odd
    0.09
     extensively
    0.09
     hard
    0.09
     primarily
    0.08
     hardest
    0.08
     commercially
    0.08
    odd
    0.08
     as
    0.07
     unsuccessfully
    0.07
    Odd
    0.07
    Activations Density 0.102%

    No Known Activations