© 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. 26453
    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
    pone
    -0.10
     crunch
    -0.10
    etro
    -0.10
     intermittent
    -0.09
     braking
    -0.09
    ¦
    -0.09
    itsu
    -0.09
     Whe
    -0.09
     ups
    -0.09
    -string
    -0.09
    POSITIVE LOGITS
     unfairly
    0.11
     confidently
    0.10
     sym
    0.10
     celebr
    0.10
     celebrates
    0.10
    —including
    0.10
     bast
    0.10
     invites
    0.09
     Celebr
    0.09
     invite
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.