© 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. 17743
    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
     Ther
    -0.07
    isch
    -0.07
     Karma
    -0.07
    <|fim_suffix|>
    -0.07
     Uni
    -0.07
     scissors
    -0.07
     Bast
    -0.07
     applic
    -0.07
     bastard
    -0.07
    ATE
    -0.07
    POSITIVE LOGITS
    /ws
    0.12
     prostit
    0.11
     lud
    0.11
     prostitut
    0.11
     Dirt
    0.11
     GK
    0.10
     Woodward
    0.10
     Sap
    0.10
    strup
    0.10
    hra
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.