© 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. 27242
    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
     extrav
    -0.08
     Cant
    -0.08
     suicides
    -0.08
     antid
    -0.08
     hide
    -0.08
     rehab
    -0.08
     minib
    -0.07
     suited
    -0.07
     volumes
    -0.07
     curl
    -0.07
    POSITIVE LOGITS
    urn
    0.12
     carn
    0.10
    unda
    0.10
     Explicit
    0.10
     Orch
    0.10
     Species
    0.10
     VX
    0.10
     Couples
    0.10
    azzi
    0.10
    uled
    0.10
    Activations Density 0.000%

    No Known Activations