© 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. 5529
    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
    blink
    -0.14
    tern
    -0.13
     paraph
    -0.12
    ocale
    -0.11
     Pew
    -0.11
    fcc
    -0.11
    -Star
    -0.11
    -pad
    -0.10
     seam
    -0.10
     -------------------------------------------------------------------------
    -0.10
    POSITIVE LOGITS
     Rah
    0.07
     dep
    0.06
     psychic
    0.06
     inde
    0.06
     congen
    0.06
    itra
    0.06
     Gst
    0.06
     trader
    0.06
     Chew
    0.06
     Guth
    0.06
    Activations Density 0.000%

    No Known Activations