© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    each other and interrelations

    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
     OE
    -0.11
    amera
    -0.10
     others
    -0.10
    tre
    -0.09
     eux
    -0.09
     altogether
    -0.09
     Vog
    -0.09
    adora
    -0.09
    others
    -0.09
    itur
    -0.08
    POSITIVE LOGITS
     respective
    0.10
    ukan
    0.10
    inks
    0.10
    leys
    0.09
     CM
    0.09
    angs
    0.09
    ^K
    0.09
    achts
    0.09
    ande
    0.09
    zung
    0.09
    Activations Density 0.046%

    No Known Activations