© 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. 117231
    Prev
    Next
    INDEX
    Explanations

    distributed with this source code

    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
     Quarter
    -0.10
    otts
    -0.10
    kon
    -0.10
    ecz
    -0.09
    arel
    -0.09
    lsa
    -0.09
    kus
    -0.09
    atro
    -0.09
    orde
    -0.09
    order
    -0.08
    POSITIVE LOGITS
    quals
    0.11
     hed
    0.10
    unset
    0.09
     Dor
    0.09
     Twe
    0.09
     xor
    0.09
    æľ¬
    0.09
    {_
    0.09
     Mig
    0.09
     Nash
    0.08
    Activations Density 0.001%

    No Known Activations