© 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. 113607
    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
    pes
    -0.12
    sto
    -0.12
    stag
    -0.11
    @author
    -0.11
     tl
    -0.11
     stag
    -0.11
    prototype
    -0.11
    -bo
    -0.11
    actable
    -0.11
    ect
    -0.11
    POSITIVE LOGITS
     confirmed
    0.08
     confirming
    0.08
     Circ
    0.08
    acier
    0.07
     Angels
    0.07
    Confirm
    0.07
    DateTime
    0.07
     Burl
    0.07
     wholes
    0.06
     border
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.