© 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. 34132
    Prev
    Next
    INDEX
    Explanations

    apart from

    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
    Views
    -0.11
    untu
    -0.10
     ath
    -0.09
     nostalg
    -0.08
    YS
    -0.08
     excl
    -0.08
     tipped
    -0.08
     grouping
    -0.08
     prefect
    -0.08
     labyrinth
    -0.08
    POSITIVE LOGITS
     quietly
    0.12
     awaiting
    0.10
     uneasy
    0.10
     revolving
    0.10
     nerv
    0.10
     patiently
    0.10
     watching
    0.10
     pepper
    0.10
     waiting
    0.10
     stays
    0.10
    Activations Density 0.055%

    No Known Activations