© 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. 115024
    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
     Jeh
    -0.09
     respectively
    -0.09
     abstraction
    -0.09
     pomp
    -0.09
    ICC
    -0.08
    /ts
    -0.08
    Communic
    -0.08
     carrying
    -0.08
    po
    -0.08
     dil
    -0.08
    POSITIVE LOGITS
    autos
    0.10
     confl
    0.10
     lev
    0.09
     meis
    0.09
     MILF
    0.09
    {text
    0.09
    opa
    0.09
     frags
    0.09
     spawned
    0.08
    ì¹
    0.08
    Activations Density 0.000%

    No Known Activations