© 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. 116944
    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
    aldi
    -0.09
     resid
    -0.09
    ija
    -0.09
     themselves
    -0.09
    /li
    -0.09
     Boh
    -0.09
    DS
    -0.09
    opo
    -0.09
     Ain
    -0.09
    eor
    -0.09
    POSITIVE LOGITS
     fulfill
    0.13
     fulfilling
    0.11
     fulfil
    0.10
    atern
    0.10
     fj
    0.10
     ful
    0.09
     Ful
    0.09
     fulfilled
    0.09
     earthly
    0.09
     Kill
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.