© 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. 30610
    Prev
    Next
    INDEX
    Explanations

    Hartford, Raleigh, Angelo, currency, ibition

    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
     headed
    -0.10
     boarded
    -0.10
    mans
    -0.09
    iez
    -0.09
    hawks
    -0.09
    /bus
    -0.09
     scrolled
    -0.09
    hir
    -0.09
     chaired
    -0.08
     заг
    -0.08
    POSITIVE LOGITS
     Wick
    0.11
    /we
    0.10
     em
    0.09
    seg
    0.09
     wo
    0.09
     defe
    0.09
    zier
    0.09
     eyewitness
    0.09
    'l
    0.09
     girl
    0.08
    Activations Density 0.001%

    No Known Activations