© 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. 88444
    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
     bip
    -0.13
     Bip
    -0.10
    -color
    -0.10
    bir
    -0.10
     bubbles
    -0.10
    SSF
    -0.10
    oeff
    -0.10
    ereg
    -0.10
    FFE
    -0.10
    inscription
    -0.10
    POSITIVE LOGITS
     something
    0.08
    gom
    0.08
     interesse
    0.08
    /fast
    0.08
     herself
    0.07
     drawers
    0.07
    lover
    0.07
     fabric
    0.07
     closures
    0.07
    ipur
    0.07
    Activations Density 0.000%

    No Known Activations