© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 91917
    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
     Wel
    -0.10
    lage
    -0.09
     excellence
    -0.09
    reff
    -0.09
    enda
    -0.09
    aye
    -0.09
    лав
    -0.09
     mar
    -0.09
    [:]
    -0.09
    onden
    -0.08
    POSITIVE LOGITS
     Higgins
    0.09
    rosis
    0.08
    (from
    0.08
     Cities
    0.08
    indsight
    0.08
     Terr
    0.08
     Tart
    0.08
    agu
    0.08
     fringe
    0.08
     Apocalypse
    0.08
    Activations Density 0.000%

    No Known Activations