© 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. 117437
    Prev
    Next
    INDEX
    Explanations

    cannot run or must upgrade

    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
    holm
    -0.10
     uphill
    -0.10
     Kai
    -0.10
    Routine
    -0.10
     unnecessary
    -0.09
     Routine
    -0.09
     anytime
    -0.09
     REAL
    -0.09
     seldom
    -0.09
    Virgin
    -0.09
    POSITIVE LOGITS
    must
    0.12
     must
    0.12
     MUST
    0.11
    å¿ħ
    0.11
     Coron
    0.11
    rox
    0.11
    Must
    0.10
    unpack
    0.10
    allon
    0.10
     å¿
    0.10
    Activations Density 0.233%

    No Known Activations