© 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. 111802
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     exploding
    -0.09
    nst
    -0.09
     Hob
    -0.09
    -backed
    -0.08
     diagon
    -0.08
     liter
    -0.08
     Harr
    -0.08
     Daniels
    -0.08
    dorf
    -0.08
    nr
    -0.08
    POSITIVE LOGITS
     repro
    0.11
    aser
    0.10
    icc
    0.10
    esi
    0.10
     ponder
    0.10
     równ
    0.10
    ecer
    0.09
     consensus
    0.09
     tec
    0.09
     diplomatic
    0.09
    Activations Density 0.000%

    No Known Activations