© 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. 112512
    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
     disin
    -0.13
     Proud
    -0.10
    -desc
    -0.10
     vacancy
    -0.10
     famously
    -0.09
     brun
    -0.09
     Paz
    -0.09
     foremost
    -0.09
     sunset
    -0.09
     descended
    -0.09
    POSITIVE LOGITS
     Patron
    0.10
    occ
    0.10
     Abr
    0.09
     undocumented
    0.09
     patrons
    0.09
     impress
    0.09
     finger
    0.08
    ERRU
    0.08
    UDO
    0.08
    qus
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.