© 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. 116794
    Prev
    Next
    INDEX
    Explanations

    debauchery, debiased, debacle, debonded

    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
     inferred
    -0.10
     Cyr
    -0.10
    otos
    -0.10
    sn
    -0.10
     concurrent
    -0.10
    sig
    -0.09
    aways
    -0.09
    silver
    -0.09
     interior
    -0.09
    alin
    -0.09
    POSITIVE LOGITS
     deb
    0.11
    ilitation
    0.10
     debacle
    0.10
    iard
    0.09
     bare
    0.09
     cour
    0.09
    iado
    0.09
     ary
    0.09
    aad
    0.09
     nob
    0.09
    Activations Density 0.004%

    No Known Activations