© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33992
    Prev
    Next
    INDEX
    Explanations

    retrieval or insertion

    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
    Negative Logits
     ingest
    -0.09
    star
    -0.09
    ali
    -0.09
    sr
    -0.09
    mr
    -0.09
     Corona
    -0.08
     Kiss
    -0.08
     shrinking
    -0.08
    shr
    -0.08
     profil
    -0.08
    POSITIVE LOGITS
     retrieval
    0.11
     retrieving
    0.11
     retrieved
    0.11
     therein
    0.11
     Barb
    0.10
    eldo
    0.10
     heraus
    0.10
    orrh
    0.10
     displ
    0.10
     widening
    0.10
    Activations Density 0.036%

    No Known Activations