© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    ways to quit or support us

    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
     bare
    -0.08
     flo
    -0.07
     Shaw
    -0.07
     crosses
    -0.07
    pst
    -0.07
    lep
    -0.07
     tran
    -0.07
     solves
    -0.07
     shar
    -0.06
    nost
    -0.06
    POSITIVE LOGITS
    .lists
    0.11
    -cond
    0.10
     devant
    0.10
     usur
    0.10
    /by
    0.10
     zad
    0.10
     tup
    0.10
    671
    0.10
     Sach
    0.10
    FAQ
    0.10
    Activations Density 0.068%

    No Known Activations