© 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. 116246
    Prev
    Next
    INDEX
    Explanations

    other entities, items, computers, people

    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
    isas
    -0.12
    kest
    -0.09
    idar
    -0.09
    cg
    -0.09
    iros
    -0.09
     revers
    -0.09
     Others
    -0.09
     hol
    -0.09
    pty
    -0.09
    isa
    -0.09
    POSITIVE LOGITS
     equally
    0.11
     Fah
    0.09
     Rae
    0.09
     themselves
    0.09
     Bust
    0.09
     ones
    0.09
    URITY
    0.09
     Consolid
    0.09
     peers
    0.09
     Yao
    0.08
    Activations Density 0.144%

    No Known Activations