© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27393
    Prev
    Next
    INDEX
    Explanations

    lanugo, lanthanide, lantern, Lanark, Laney, Lanphere

    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
    Not in Any Lists

    No Comments

    Negative Logits
     stripped
    -0.09
    uento
    -0.09
    o
    -0.09
    iy
    -0.09
    ritos
    -0.09
    ration
    -0.08
     comple
    -0.08
     multim
    -0.08
    itÃł
    -0.08
     Alto
    -0.08
    POSITIVE LOGITS
    ifr
    0.11
    Ñĥж
    0.11
    ophon
    0.11
    orr
    0.10
    ing
    0.10
    ingroup
    0.10
    enga
    0.10
    fram
    0.10
     Lansing
    0.10
    xon
    0.10
    Activations Density 0.002%

    No Known Activations