© 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. 27758
    Prev
    Next
    INDEX
    Explanations

    malfunction or dysfunction

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    身
    -0.11
     body
    -0.10
     usher
    -0.10
     spine
    -0.10
     cyn
    -0.09
     cancell
    -0.09
     Arb
    -0.09
     adherence
    -0.09
     cancelled
    -0.09
     Oliv
    -0.09
    POSITIVE LOGITS
     dysfunction
    0.15
     Dysfunction
    0.14
     neglect
    0.14
     treatments
    0.13
     malfunction
    0.13
     functionality
    0.12
     tam
    0.12
     stimulation
    0.12
     manipulation
    0.12
     usage
    0.12
    Activations Density 0.708%

    No Known Activations