© 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. 24937
    Prev
    Next
    INDEX
    Explanations

    archway, arches, archipelagic, archaic

    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
     inline
    -0.08
    cheid
    -0.08
     enclosed
    -0.08
    -kit
    -0.08
     Dou
    -0.08
     att
    -0.08
     sack
    -0.08
    istik
    -0.08
    itchen
    -0.08
    ders
    -0.08
    POSITIVE LOGITS
     eyebrows
    0.16
    itr
    0.14
    itect
    0.14
     arch
    0.13
    angel
    0.13
    /arch
    0.13
    ÃŃv
    0.12
    ipel
    0.12
    aic
    0.12
     nem
    0.12
    Activations Density 0.014%

    No Known Activations