© 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. 50202
    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
     budding
    -0.09
     wast
    -0.09
    lar
    -0.09
     Pear
    -0.08
     bl
    -0.08
     Dew
    -0.08
    uns
    -0.08
     climbing
    -0.08
    cw
    -0.07
    hor
    -0.07
    POSITIVE LOGITS
     Lun
    0.11
    ForObject
    0.11
     lag
    0.10
    atel
    0.10
     Homepage
    0.10
     Lag
    0.10
     personn
    0.09
     terra
    0.09
     Morg
    0.09
     inde
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.