© 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. 88495
    Prev
    Next
    INDEX
    Explanations

    slur, slurry, Spanish

    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
     Traverse
    -0.09
    autor
    -0.08
     assort
    -0.08
     provisioning
    -0.08
     orm
    -0.08
     traverse
    -0.08
    odb
    -0.08
     flush
    -0.08
     superf
    -0.08
    VAS
    -0.07
    POSITIVE LOGITS
    ily
    0.13
    /sl
    0.13
     words
    0.12
     pronunciation
    0.11
    abic
    0.11
     slightly
    0.10
     saliva
    0.10
    words
    0.10
    edly
    0.10
    ise
    0.10
    Activations Density 0.001%

    No Known Activations