© 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. 25206
    Prev
    Next
    INDEX
    Explanations

    Tat/Gor followed by names or places

    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
    idar
    -0.11
    esse
    -0.11
    aru
    -0.10
     prov
    -0.10
    ntag
    -0.10
    a
    -0.09
    eson
    -0.09
    esen
    -0.09
     dude
    -0.09
    izu
    -0.09
    POSITIVE LOGITS
    iana
    0.10
     skeletal
    0.08
     retro
    0.08
    /groups
    0.08
    fur
    0.08
     brittle
    0.08
    pal
    0.08
     sprint
    0.07
     apparent
    0.07
     qualification
    0.07
    Activations Density 0.006%

    No Known Activations