© 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. 28585
    Prev
    Next
    INDEX
    Explanations

    information technology and systems

    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
    efa
    -0.13
    ptions
    -0.11
    unya
    -0.11
    (es
    -0.11
    eness
    -0.10
    tings
    -0.10
    usu
    -0.10
    CHE
    -0.09
     unin
    -0.09
    ped
    -0.09
    POSITIVE LOGITS
    ally
    0.18
     overload
    0.14
    ALLY
    0.14
     about
    0.13
    -processing
    0.12
    -intensive
    0.11
     gathering
    0.11
     asym
    0.11
     dissemination
    0.11
    -sharing
    0.11
    Activations Density 0.095%

    No Known Activations