© 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. 49670
    Prev
    Next
    INDEX
    Explanations

    parent/slug/measuring/permalink identifiers

    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
    atab
    -0.08
     Dag
    -0.08
     tol
    -0.08
     damn
    -0.07
     darn
    -0.07
    chang
    -0.07
    rog
    -0.07
     Anth
    -0.07
     certainly
    -0.07
    pies
    -0.07
    POSITIVE LOGITS
     Fus
    0.10
    nej
    0.10
    inters
    0.10
     deix
    0.10
     tri
    0.10
     Sta
    0.10
    ibox
    0.10
     Suff
    0.09
     preamble
    0.09
    entic
    0.09
    Activations Density 0.001%

    No Known Activations