© 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. 34020
    Prev
    Next
    INDEX
    Explanations

    `.` or `/` followed by specific terms

    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
    DMI
    -0.08
    enk
    -0.08
     necessarily
    -0.07
    misc
    -0.07
     hairy
    -0.07
     inverted
    -0.07
     Woodward
    -0.07
     fancy
    -0.07
    ninger
    -0.07
    _ser
    -0.06
    POSITIVE LOGITS
     Wig
    0.12
     Chatt
    0.11
    ials
    0.11
    mf
    0.11
    elves
    0.11
     unknown
    0.11
     kr
    0.11
     Forgot
    0.10
     forgotten
    0.10
    SENT
    0.10
    Activations Density 0.001%

    No Known Activations