© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115336
    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
    adge
    -0.09
     sens
    -0.07
     NRA
    -0.07
     grap
    -0.07
    iram
    -0.07
    rix
    -0.07
    nos
    -0.07
    Sessions
    -0.07
     JSON
    -0.06
     grat
    -0.06
    POSITIVE LOGITS
     Resident
    0.12
    mant
    0.12
     loft
    0.11
     Blanco
    0.11
     resident
    0.11
     stamped
    0.11
     dread
    0.11
     Lah
    0.10
     joked
    0.10
    SourceType
    0.10
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.