© 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. 49532
    Prev
    Next
    INDEX
    Explanations

    intended or destined for a purpose

    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
    ador
    -0.08
     optimal
    -0.08
    ton
    -0.08
     hast
    -0.07
     rever
    -0.07
    pare
    -0.07
     and
    -0.07
     Hawk
    -0.07
    odd
    -0.07
    elle
    -0.07
    POSITIVE LOGITS
    enting
    0.11
     meant
    0.11
     dest
    0.10
     Cuban
    0.10
     geom
    0.10
    Enumerator
    0.09
     mate
    0.09
    hire
    0.09
    PLACE
    0.09
     commissions
    0.09
    Activations Density 0.007%

    No Known Activations